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

    Neuronpedia

    INDEX
    Explanations

    references to entities or concepts in various contexts

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

    Possessive pronouns followed by a descriptive adjective

    np_acts-logits-general · gemini-2.0-flash

    described in full

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.73
    tvguidetime
    -0.72
    afficheront
    -0.69
    ագրություններ
    -0.68
    Билгалдахарш
    -0.67
    Примітки
    -0.67
     typelib
    -0.66
     InputDecoration
    -0.65
    Referanser
    -0.64
    awtextra
    -0.64
    POSITIVE LOGITS
     entirety
    0.74
     completos
    0.71
     completas
    0.61
    følgelig
    0.57
     complete
    0.56
     completo
    0.55
    Forms
    0.52
     totality
    0.51
     its
    0.51
     full
    0.50
    Act Density 0.149%

    No Known Activations