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

    Neuronpedia

    INDEX
    Explanations

    code and math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    能力
    -0.07
     chores
    -0.06
     /=
    -0.06
     rekl
    -0.06
    ’autres
    -0.06
    _prices
    -0.06
     sais
    -0.06
     Switzerland
    -0.06
     Stores
    -0.06
    -platform
    -0.06
    POSITIVE LOGITS
    fft
    0.07
    WF
    0.06
    lashes
    0.06
    -query
    0.06
    point
    0.06
    engan
    0.06
     semantic
    0.06
    emes
    0.06
    .Rotate
    0.06
     contrasting
    0.06
    Act Density 0.081%

    No Known Activations