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

    Neuronpedia

    INDEX
    Explanations

    ot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đầy
    -0.08
     Fer
    -0.07
    -ng
    -0.07
     nationwide
    -0.07
     фиг
    -0.06
    _FALL
    -0.06
     cough
    -0.06
    楷
    -0.06
     methodology
    -0.06
    .templates
    -0.06
    POSITIVE LOGITS
    枥
    0.07
     окру
    0.07
    cae
    0.07
    ichage
    0.07
    outine
    0.07
    ushed
    0.07
     onData
    0.07
    roke
    0.07
    镥
    0.07
    솊
    0.07
    Act Density 0.001%

    No Known Activations