Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to actions and entities in a computational or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following specific two-letter combinations

    np_acts-logits-general · gemini-2.0-flash

    arpeggiate, genetically differentiate, air scent, second-guess, interpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transforma
    -0.63
     Majefty
    -0.60
    一見
    -0.56
    ſelf
    -0.56
     iſt
    -0.55
     eſt
    -0.53
    stolen
    -0.52
     onPostExecute
    -0.51
     vira
    -0.50
     worn
    -0.50
    POSITIVE LOGITS
     Himo
    0.63
     Bourgoin
    0.62
    MethodManager
    0.61
     them
    0.58
     חיצוניים
    0.57
    principalColumn
    0.56
     CascadeType
    0.54
    💼
    0.54
     jotka
    0.54
     tänka
    0.53
    Act Density 0.384%

    No Known Activations