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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weir
    -0.06
    _REUSE
    -0.06
     Ρ
    -0.06
    cles
    -0.06
    dds
    -0.06
     ids
    -0.06
    行动
    -0.06
    Coding
    -0.06
    ENU
    -0.06
    :id
    -0.06
    POSITIVE LOGITS
     stable
    0.07
     uz
    0.06
    consider
    0.06
     uom
    0.06
     Loy
    0.06
     match
    0.06
     Reyn
    0.06
    Love
    0.06
     Ф
    0.06
    іла
    0.06
    Act Density 0.002%

    No Known Activations