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

    Neuronpedia

    INDEX
    Explanations

    199

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Capability
    -0.07
    _PRIMARY
    -0.06
     Operations
    -0.06
     baptized
    -0.06
    filesystem
    -0.06
     Constant
    -0.06
     insurer
    -0.06
     abi
    -0.06
     Mandela
    -0.06
     diferencia
    -0.06
    POSITIVE LOGITS
    loyd
    0.07
     shady
    0.07
    شن
    0.07
     remainder
    0.06
     좋
    0.06
     Λα
    0.06
    /*!↵
    0.06
    ж
    0.06
    ｿ
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations