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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DEBUG
    -0.07
     слыш
    -0.07
     leakage
    -0.06
    '};↵
    -0.06
     لها
    -0.06
    Password
    -0.06
     روند
    -0.06
     ダ
    -0.06
     correlates
    -0.06
    auty
    -0.06
    POSITIVE LOGITS
    atab
    0.06
    ahr
    0.06
    wc
    0.06
     счит
    0.06
    INFO
    0.06
     pageTitle
    0.06
    Theo
    0.06
    lias
    0.06
     місто
    0.06
    .Solid
    0.06
    Act Density 0.000%

    No Known Activations