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

    Neuronpedia

    INDEX
    Explanations

    ARS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Navigation
    -0.07
    producer
    -0.07
    ivism
    -0.06
    ゞ
    -0.06
    _IMP
    -0.06
     hlavní
    -0.06
     interests
    -0.06
     silent
    -0.06
     جو
    -0.06
    تامبر
    -0.06
    POSITIVE LOGITS
    ARS
    0.08
     cous
    0.07
    ars
    0.07
     Took
    0.06
     SAR
    0.06
     Wax
    0.06
     Percent
    0.06
     Rad
    0.06
     Studi
    0.06
    ΟΥΣ
    0.06
    Act Density 0.001%

    No Known Activations