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

    Neuronpedia

    INDEX
    Explanations

    university

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nul
    -0.07
    ár
    -0.07
    土地
    -0.06
    noun
    -0.06
    �
    -0.06
    ladesh
    -0.06
    adders
    -0.06
    ó
    -0.06
    -To
    -0.06
    ulus
    -0.06
    POSITIVE LOGITS
    blem
    0.06
     gradual
    0.06
    _wr
    0.06
     Derrick
    0.06
    0.06
    icot
    0.06
     JS
    0.06
     abnormal
    0.06
    υκ
    0.06
     ند
    0.06
    Act Density 0.005%

    No Known Activations