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

    Neuronpedia

    INDEX
    Explanations

    phrases that express the desire to create or craft something manually

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

    Follows verbs that describe actions or experiences

    np_acts-logits-general · gemini-2.0-flash

    code or function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Erreferentziak
    -0.66
    enumi
    -0.63
    Personendaten
    -0.63
    agissait
    -0.56
     essentiels
    -0.56
     πως
    -0.55
     تانيه
    -0.54
    beispiel
    -0.54
    FYI
    -0.54
    彿
    -0.54
    POSITIVE LOGITS
    dafx
    0.61
     "").
    0.60
    Such
    0.59
    ))).
    0.58
    )))
    0.58
     =)
    0.57
    )))
    0.56
    ))))))))
    0.56
    runApp
    0.55
     "".
    0.55
    Act Density 0.098%

    No Known Activations