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

    Neuronpedia

    INDEX
    Explanations

    NaN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �이
    -0.07
    ilerinin
    -0.07
     аб
    -0.07
    ’av
    -0.06
     nová
    -0.06
     DY
    -0.06
    規
    -0.06
    序
    -0.06
    .over
    -0.06
     Welch
    -0.06
    POSITIVE LOGITS
     NaN
    0.20
     aka
    0.19
     outliers
    0.13
    NaN
    0.12
     sapi
    0.10
     outlier
    0.09
    .NaN
    0.09
    aka
    0.06
    SA
    0.06
    _frontend
    0.06
    Act Density 0.003%

    No Known Activations