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

    Neuronpedia

    INDEX
    Explanations

    hate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >>()
    -0.07
    raman
    -0.06
    alarında
    -0.06
     موجب
    -0.06
     communal
    -0.06
    dirty
    -0.06
     terrestrial
    -0.06
    .Program
    -0.06
    _dimensions
    -0.06
     sho
    -0.06
    POSITIVE LOGITS
     love
    0.07
    leanup
    0.06
     staples
    0.06
    erti
    0.06
    _exists
    0.06
     VECTOR
    0.06
     복
    0.06
     profiles
    0.06
    _callable
    0.06
     hashtags
    0.06
    Act Density 0.001%

    No Known Activations