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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    357
    -0.07
    ifo
    -0.07
     cif
    -0.07
     Lif
    -0.06
    ibu
    -0.06
    [idx
    -0.06
     lif
    -0.06
    <U
    -0.06
    _path
    -0.06
    edit
    -0.06
    POSITIVE LOGITS
     та
    0.07
    onus
    0.07
    PCS
    0.06
     �
    0.06
    /owl
    0.06
    .frequency
    0.06
    ､
    0.06
    icus
    0.06
     góc
    0.06
    植物
    0.06
    Act Density 0.055%

    No Known Activations