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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _alloc
    -0.07
    vre
    -0.07
     ny
    -0.07
    -point
    -0.07
    Wrap
    -0.06
     glorious
    -0.06
     diligent
    -0.06
     binds
    -0.06
     Atlanta
    -0.06
    -python
    -0.06
    POSITIVE LOGITS
    وف
    0.06
    977
    0.06
    [Double
    0.06
     peter
    0.06
    _fetch
    0.06
    خیص
    0.06
    _TRAIN
    0.06
    .dataset
    0.06
     SIGN
    0.06
    _Runtime
    0.06
    Act Density 0.011%

    No Known Activations