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

    Neuronpedia

    INDEX
    Explanations

    security border

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    поле
    0.82
    Aud
    0.82
     RSC
    0.81
     Rosh
    0.78
     DSP
    0.75
    omon
    0.73
    Dancing
    0.71
    летие
    0.71
    இந்
    0.70
    ಛ
    0.70
    POSITIVE LOGITS
     통
    0.74
     ترد
    0.70
     해
    0.69
     cận
    0.67
     ದ
    0.65
     সব
    0.64
     frein
    0.63
    )$:
    0.63
    &$\
    0.63
     Фурга
    0.62
    Act Density 0.000%

    No Known Activations