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

    Neuronpedia

    INDEX
    Explanations

    statements that assert truth or facticity

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

    "fact" appearing in various contexts

    np_acts-logits-general · gemini-2.0-flash

    introducing supplementary facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     awakeFromNib
    -0.69
     respective
    -0.57
     跳转至
    -0.57
    automatic
    -0.54
    TileEntity
    -0.53
    Automatic
    -0.52
    KEYCODE
    -0.52
     dragen
    -0.52
    니다
    -0.52
    Remover
    -0.51
    POSITIVE LOGITS
     almost
    0.76
     even
    0.75
     actually
    0.71
     quite
    0.71
    Bahkan
    0.69
    Saharan
    0.69
    Actually
    0.68
     Bahkan
    0.68
    actually
    0.67
    Almost
    0.67
    Act Density 0.078%

    No Known Activations