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

    Neuronpedia

    INDEX
    Explanations

    words related to potential benefits and drawbacks

    oai_token-act-pair · gemini-2.0-flash

    technical/descriptive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.56
    ConstraintMaker
    -0.56
    SPATH
    -0.54
    ogados
    -0.53
    czy
    -0.53
     Chwiliwch
    -0.53
     [][]
    -0.53
    wachs
    -0.52
    timeScale
    -0.52
     مرئيه
    -0.52
    POSITIVE LOGITS
    ьаж
    0.54
     épaules
    0.50
     fallu
    0.49
     palsu
    0.46
    ClientSize
    0.46
     Sloveniji
    0.44
     acceptor
    0.43
    ècie
    0.43
     falso
    0.42
    それで
    0.42
    Act Density 0.347%

    No Known Activations