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

    Neuronpedia

    INDEX
    Explanations

    docs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WPARAM
    -0.07
     nurse
    -0.07
    Care
    -0.07
     delegate
    -0.06
    кая
    -0.06
    良
    -0.06
    hou
    -0.06
     voter
    -0.06
    末
    -0.06
    _FRE
    -0.06
    POSITIVE LOGITS
    šk
    0.06
    .Unmarshal
    0.06
     UIBar
    0.06
     `↵
    0.06
     contentValues
    0.06
     olup
    0.06
    而
    0.06
     Assassin
    0.06
    .track
    0.06
    rp
    0.06
    Act Density 0.008%

    No Known Activations