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

    Neuronpedia

    INDEX
    Explanations

    references to legal detention and drone strikes

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

    violence, militants, police, and politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.54
    出版年
    -0.51
     صوتيه
    -0.49
     Grüsse
    -0.47
     CURIAM
    -0.43
     oreja
    -0.40
    currentColor
    -0.39
     infierno
    -0.35
    Werdegang
    -0.35
     Nuestros
    -0.34
    POSITIVE LOGITS
    ReusableCell
    0.52
    BufferException
    0.52
    IsContent
    0.50
    IsMutable
    0.48
    もちゃ
    0.47
     ""],
    0.47
    もしろ
    0.44
    VertexAttrib
    0.44
     initView
    0.43
    writeFieldEnd
    0.43
    Act Density 0.020%

    No Known Activations