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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _single
    -0.06
     onchange
    -0.06
    面议
    -0.06
     लगभग
    -0.06
    -tooltip
    -0.06
     TestUtils
    -0.06
     Haupt
    -0.06
    Principal
    -0.06
    renders
    -0.06
     infantry
    -0.06
    POSITIVE LOGITS
     happier
    0.08
    _configs
    0.07
    .SetValue
    0.07
    لود
    0.07
     colleges
    0.06
    يان
    0.06
     gắn
    0.06
    esses
    0.06
     communic
    0.06
     cre
    0.06
    Act Density 0.017%

    No Known Activations