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

    Neuronpedia

    INDEX
    Explanations

    violates my guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सिन
    0.44
    CTk
    0.40
    prosperity
    0.39
    ెంబ
    0.38
    Fl
    0.38
    antics
    0.37
    Steve
    0.37
    mv
    0.36
     ملازمت
    0.36
    vn
    0.35
    POSITIVE LOGITS
    叄
    0.43
     एक्सप्लेन
    0.43
     FRANCIS
    0.41
     previewBuilder
    0.41
     cocker
    0.39
    ждений
    0.39
    CEA
    0.39
     Consiglio
    0.39
     CCD
    0.38
     محور
    0.38
    Act Density 0.003%

    No Known Activations