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

    Neuronpedia

    INDEX
    Explanations

    company or D prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    B
    0.98
    GE
    0.82
    D
    0.80
     CE
    0.78
    Y
    0.75
     vi
    0.75
    C
    0.75
    from
    0.74
     sighted
    0.73
     B
    0.73
    POSITIVE LOGITS
     ennemis
    1.03
    nije
    1.02
     kebutuhan
    0.98
    रोग
    0.98
    ร่างกาย
    0.98
     Produk
    0.97
     permasalahan
    0.96
    slüman
    0.96
    сынын
    0.95
     potreb
    0.93
    Act Density 0.000%

    No Known Activations