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

    Neuronpedia

    INDEX
    Explanations

    words related to deception or dishonesty

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

    ending in "-su" or starting with "un-", "in-", "or-"

    np_acts-logits-general · gemini-2.0-flash

    descriptive words from prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.63
     Pingback
    -0.57
     compris
    -0.56
    出版年
    -0.56
     fubject
    -0.54
    PrototypeOf
    -0.53
     referenties
    -0.53
    attore
    -0.53
    onAttach
    -0.50
     laſt
    -0.49
    POSITIVE LOGITS
    ingly
    0.61
     enough
    0.60
    AddHtmlAttribute
    0.60
     profoundly
    0.57
    มาะ
    0.57
    Embeddable
    0.57
    agoza
    0.57
     näky
    0.56
    rabaya
    0.56
    fulness
    0.56
    Act Density 0.213%

    No Known Activations