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

    Neuronpedia

    INDEX
    Explanations

    specialized services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     big
    0.82
    яви
    0.81
    匝
    0.80
    clearInterval
    0.79
     چاندی
    0.79
    iletto
    0.76
    避け
    0.76
     النهائية
    0.75
    Italia
    0.75
    сць
    0.75
    POSITIVE LOGITS
     Args
    1.38
     __
    1.37
    __
    1.37
     supplic
    1.35
     Karak
    1.29
     RUN
    1.25
     Kazan
    1.25
     Westbrook
    1.24
     Shaw
    1.19
     PROVIDED
    1.17
    Act Density 0.164%

    No Known Activations