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

    Neuronpedia

    INDEX
    Explanations

    sorting and counting effort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    шками
    0.89
     passant
    0.87
    互相
    0.84
     inoculation
    0.82
     karit
    0.81
    anía
    0.81
    <unused71>
    0.80
    ileno
    0.79
    譯
    0.78
    тивным
    0.78
    POSITIVE LOGITS
    प
    0.75
     kabul
    0.67
    ρ
    0.67
    ുവ
    0.67
     bộ
    0.67
     leave
    0.67
    ٹر
    0.66
     पंप
    0.66
    я
    0.66
     salts
    0.66
    Act Density 0.000%

    No Known Activations