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

    Neuronpedia

    INDEX
    Explanations

    importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     walled
    -0.56
     importance
    -0.54
     ambitious
    -0.51
    OLAS
    -0.51
     IEnumerator
    -0.50
    ]._
    -0.49
    walled
    -0.48
    UAWEI
    -0.48
     intense
    -0.47
    leur
    -0.47
    POSITIVE LOGITS
    Hochspringen
    0.67
    OGND
    0.65
     مصرى
    0.64
     autorytatywna
    0.64
     оригіналу
    0.63
    GEBURTSDATUM
    0.62
     bezeichneter
    0.58
    municipi
    0.57
    RectangleBorder
    0.56
    Autoritní
    0.56
    Act Density 0.116%

    No Known Activations