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

    Neuronpedia

    INDEX
    Explanations

    nltk downloads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ням
    0.44
    nalia
    0.43
    辇
    0.41
    ॉर्डिंग
    0.37
    煂
    0.37
    foam
    0.36
    동
    0.36
    virtual
    0.36
    咵
    0.36
    㓶
    0.35
    POSITIVE LOGITS
     Desai
    0.41
     Citizenship
    0.38
     Token
    0.37
     LD
    0.37
     SQ
    0.37
     Cui
    0.36
    aran
    0.36
     Working
    0.36
     डाउन
    0.36
     build
    0.36
    Act Density 0.000%

    No Known Activations