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

    Neuronpedia

    INDEX
    Explanations

    ab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __))
    -0.07
     articulate
    -0.07
    picker
    -0.06
     indexed
    -0.06
     nécessaire
    -0.06
     karar
    -0.06
    itivity
    -0.06
    pling
    -0.06
    metry
    -0.06
    ))+
    -0.06
    POSITIVE LOGITS
    MW
    0.07
    ��
    0.07
    ี่
    0.06
     ύ
    0.06
    ===↵
    0.06
    Brit
    0.06
    _SEC
    0.06
    aybe
    0.06
     εργ
    0.06
    Four
    0.06
    Act Density 0.001%

    No Known Activations