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

    Neuronpedia

    INDEX
    Explanations

    Addressing problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ents
    -0.06
     Transformer
    -0.06
     Organizations
    -0.06
     cond
    -0.06
    接
    -0.06
     housed
    -0.06
    仕
    -0.05
    ριστ
    -0.05
    .after
    -0.05
    soles
    -0.05
    POSITIVE LOGITS
    Aura
    0.07
    .palette
    0.07
    []):
    0.07
    WAIT
    0.06
    _TEM
    0.06
     Napoli
    0.06
    printer
    0.06
    _UClass
    0.06
     Prahy
    0.06
    اختی
    0.06
    Act Density 0.037%

    No Known Activations