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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to animal attributes or properties

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

    Code snippets with "self" or similar terms

    np_acts-logits-general · gemini-2.0-flash

    switch self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onError
    -0.46
    Бележки
    -0.46
     decirle
    -0.39
    那是
    -0.38
    ADOR
    -0.38
     sī
    -0.38
    под
    -0.38
     Nacionales
    -0.37
     رف
    -0.37
     Handling
    -0.37
    POSITIVE LOGITS
     myself
    0.76
    principalColumn
    0.72
    myself
    0.71
     undersigned
    0.70
    脚注の使い方
    0.69
     myſelf
    0.68
    self
    0.67
    Myself
    0.66
     ourselves
    0.66
    AndEndTag
    0.64
    Act Density 0.306%

    No Known Activations