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

    Neuronpedia

    INDEX
    Explanations

    Character abilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mess
    -0.08
    variants
    -0.06
     Metric
    -0.06
     mirrored
    -0.06
     initializing
    -0.06
    ालय
    -0.06
    141
    -0.06
     различные
    -0.06
    .expires
    -0.06
    レー
    -0.06
    POSITIVE LOGITS
     {})↵
    0.07
     manera
    0.06
    ($(".
    0.06
    prot
    0.06
    جات
    0.06
    _WATER
    0.06
    025
    0.06
     sensation
    0.06
    INGS
    0.06
    }`}>↵
    0.06
    Act Density 0.033%

    No Known Activations