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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ắc
    -0.08
    عد
    -0.07
    'en
    -0.07
     reunited
    -0.07
    Tri
    -0.07
     writeTo
    -0.06
    笑着说
    -0.06
    -Encoding
    -0.06
    往
    -0.06
    北汽
    -0.06
    POSITIVE LOGITS
     SVM
    0.08
     ponto
    0.07
    registro
    0.07
    면
    0.07
     Makes
    0.07
     "*.
    0.07
    _gshared
    0.07
    month
    0.07
     ultimo
    0.07
    櫆
    0.07
    Act Density 0.017%

    No Known Activations