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

    Neuronpedia

    INDEX
    Explanations

    meta charset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    weder
    -0.98
    rafa
    -0.94
     talvez
    -0.92
    covi
    -0.85
     TÉCN
    -0.84
    姣
    -0.84
    igurumi
    -0.84
     pouvons
    -0.82
    adaran
    -0.82
    ngay
    -0.81
    POSITIVE LOGITS
     charset
    1.50
     http
    1.08
    http
    1.02
    charset
    0.91
     META
    0.87
    equiv
    0.85
    語言
    0.83
     HTTP
    0.83
     name
    0.82
     meta
    0.81
    Act Density 0.014%

    No Known Activations