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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DIGEST
    -0.08
    �
    -0.07
     bmi
    -0.07
     בינ
    -0.07
     Edition
    -0.07
    垕
    -0.07
     joe
    -0.07
    UPS
    -0.06
    육
    -0.06
     noen
    -0.06
    POSITIVE LOGITS
     and
    0.07
     rho
    0.07
     Ком
    0.07
     pudo
    0.07
     Latvia
    0.07
    isEnabled
    0.07
    .Close
    0.07
    �
    0.07
     the
    0.07
     informations
    0.07
    Act Density 0.003%

    No Known Activations