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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    犸
    1.97
    дите
    1.80
    Luego
    1.71
     desactiv
    1.68
    ktionen
    1.64
    द्योगिकी
    1.64
    Kalau
    1.63
     Pfarr
    1.62
     Luego
    1.61
    Пред
    1.61
    POSITIVE LOGITS
    ات
    1.68
    at
    1.67
    ிஸ்த
    1.60
    erent
    1.59
    い
    1.58
    aat
    1.55
    er
    1.55
    ्यता
    1.54
     FACS
    1.54
    sag
    1.53
    Act Density 0.000%

    No Known Activations