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

    Neuronpedia

    INDEX
    Explanations

    Note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KEEP
    -0.07
     polož
    -0.07
    -cross
    -0.06
     Lage
    -0.06
     numeros
    -0.06
    122
    -0.06
     plight
    -0.06
    123
    -0.06
    #undef
    -0.06
     Mayıs
    -0.06
    POSITIVE LOGITS
    Unavailable
    0.07
     freshly
    0.06
    ambia
    0.06
    _to
    0.06
     annotate
    0.06
     finalists
    0.06
     و
    0.06
     تولید
    0.06
    0.06
     Automatic
    0.06
    Act Density 0.000%

    No Known Activations