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

    Neuronpedia

    INDEX
    Explanations

    Acknowledgment/Validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extrav
    -0.07
     نسخ
    -0.06
    Expert
    -0.06
     câ
    -0.06
     etkili
    -0.06
    Specific
    -0.06
    izard
    -0.06
    وت
    -0.06
    §Ã
    -0.06
    rieben
    -0.06
    POSITIVE LOGITS
     IPs
    0.07
    ucs
    0.07
    *c
    0.07
    （
    0.06
    』
    0.06
    __↵
    0.06
     модели
    0.06
    =↵↵
    0.06
     ing
    0.06
    	addr
    0.06
    Act Density 0.148%

    No Known Activations