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

    Neuronpedia

    INDEX
    Explanations

    contrast and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.97
     Honestly
    1.95
    [,-
    1.94
     Preferably
    1.92
     må
    1.87
     prostu
    1.85
    ˶
    1.84
    enschaft
    1.84
     invoicing
    1.82
    绎
    1.81
    POSITIVE LOGITS
    ন
    2.45
    tól
    2.29
    ن
    2.19
    ни
    2.12
    н
    2.03
    l
    1.98
    न
    1.95
    edged
    1.95
    h
    1.86
     уж
    1.78
    Act Density 0.004%

    No Known Activations