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

    Neuronpedia

    INDEX
    Explanations

    mentioning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manual
    -0.08
     Bayesian
    -0.07
     tolua
    -0.07
    illa
    -0.07
    _inter
    -0.07
    azon
    -0.07
     Laguna
    -0.07
    (final
    -0.07
    鲩
    -0.07
    יבו
    -0.06
    POSITIVE LOGITS
    נז
    0.07
     kto
    0.07
     CIT
    0.07
     fatalities
    0.07
    //================================================================================
    0.07
    }">↵
    0.07
    ,'"
    0.06
    Rnd
    0.06
    >")↵
    0.06
    .',
↵
    0.06
    Act Density 0.000%

    No Known Activations