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

    Neuronpedia

    INDEX
    Explanations

    data availability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Func
    -0.06
    (row
    -0.06
     Thy
    -0.06
     Represents
    -0.06
    Brad
    -0.06
     cheaper
    -0.06
    xFB
    -0.06
    Sat
    -0.06
     Mystic
    -0.06
     网
    -0.06
    POSITIVE LOGITS
    enza
    0.07
     Libre
    0.07
    ामग
    0.07
    HideInInspector
    0.07
     бать
    0.07
     yanı
    0.07
     conforms
    0.06
     muddy
    0.06
    rouch
    0.06
    keeping
    0.06
    Act Density 0.031%

    No Known Activations