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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DBHelper
    -0.08
    anch
    -0.07
    舉
    -0.07
     Further
    -0.07
    ο
    -0.07
    ogenic
    -0.07
    קשה
    -0.07
     history
    -0.07
     devel
    -0.07
    atement
    -0.07
    POSITIVE LOGITS
    ["$
    0.07
    مراكز
    0.07
     regularization
    0.07
    истем
    0.07
    โปร
    0.07
    煃
    0.07
    рис
    0.07
    sının
    0.06
    _"+
    0.06
    玛丽
    0.06
    Act Density 0.014%

    No Known Activations