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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اهمیت
    -0.07
    ten
    -0.07
     minHeight
    -0.06
    ire
    -0.06
     الول
    -0.06
    awaiter
    -0.06
     pier
    -0.06
     kalk
    -0.06
     correction
    -0.06
     خد
    -0.06
    POSITIVE LOGITS
     інтер
    0.07
    Runner
    0.07
     emp
    0.07
    áže
    0.07
    ELCOME
    0.07
    皆
    0.07
    _SW
    0.06
    finance
    0.06
    _LOWER
    0.06
    -Shirt
    0.06
    Act Density 0.001%

    No Known Activations