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

    Neuronpedia

    INDEX
    Explanations

    https

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bom
    -0.08
    وری
    -0.07
    .portal
    -0.07
     ei
    -0.07
    (ar
    -0.07
    _bad
    -0.07
     sexdate
    -0.07
     Clintons
    -0.07
    (Bitmap
    -0.07
     CHP
    -0.06
    POSITIVE LOGITS
     subclasses
    0.06
    ỉnh
    0.05
    ,__
    0.05
    ическая
    0.05
    _idx
    0.05
     nicely
    0.05
     involve
    0.05
     현대
    0.05
    023
    0.05
    Maker
    0.05
    Act Density 0.001%

    No Known Activations