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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kul
    -0.07
    13
    -0.07
    Crear
    -0.07
     mantener
    -0.06
    42
    -0.06
    ička
    -0.06
     Keep
    -0.06
    ób
    -0.06
    OLID
    -0.06
    logout
    -0.06
    POSITIVE LOGITS
    阶段
    0.07
    -we
    0.07
     ull
    0.07
    }?
    0.06
    conds
    0.06
    师
    0.06
    /.↵↵
    0.06
    ataires
    0.06
     onde
    0.06
    _SURFACE
    0.06
    Act Density 0.045%

    No Known Activations