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

    Neuronpedia

    INDEX
    Explanations

    key performance indicators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Problem
    -0.08
    =name
    -0.07
    सत
    -0.07
     Bulg
    -0.07
    Split
    -0.07
     роботу
    -0.07
     Polygon
    -0.06
     Situation
    -0.06
    ivalent
    -0.06
     Rand
    -0.06
    POSITIVE LOGITS
    -awesome
    0.07
    IFICATIONS
    0.06
     qualities
    0.06
    _compare
    0.06
     управ
    0.06
     Dawson
    0.06
    Returning
    0.06
     admission
    0.06
     hurl
    0.06
     appealing
    0.06
    Act Density 0.020%

    No Known Activations