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

    Neuronpedia

    INDEX
    Explanations

    words related to conducting research

    oai_token-act-pair · gemini-2.0-flash

    random snippets of text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Véxase
    -0.50
    fromnode
    -0.50
     nakalista
    -0.48
     lại
    -0.48
     always
    -0.47
    Manbalar
    -0.45
     quickly
    -0.44
     विश्वसनीयता
    -0.44
    everywhere
    -0.43
     throughout
    -0.43
    POSITIVE LOGITS
     Shakspeare
    0.70
     Agamemnon
    0.68
     TType
    0.67
     hentai
    0.65
     fubject
    0.64
     reaſon
    0.63
     whoſe
    0.63
    sizeCache
    0.62
     auffi
    0.61
     perfons
    0.61
    Act Density 13.235%

    No Known Activations