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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Büyük
    -0.07
     elem
    -0.07
    Patch
    -0.07
    anga
    -0.07
    _addresses
    -0.06
    Bias
    -0.06
    (ent
    -0.06
     peer
    -0.06
     kwargs
    -0.06
    _reverse
    -0.06
    POSITIVE LOGITS
    "};
↵
    0.07
    вор
    0.07
     müş
    0.06
    Decode
    0.06
     dispenser
    0.06
     mientras
    0.06
     bulunur
    0.06
     Donate
    0.06
    _likes
    0.06
     آموزشی
    0.06
    Act Density 0.180%

    No Known Activations