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
    _upper
    -0.07
    ła
    -0.07
    oví
    -0.07
     columnIndex
    -0.07
    .Buffer
    -0.07
    .interface
    -0.06
     +=
    -0.06
    _Two
    -0.06
     something
    -0.06
     advising
    -0.06
    POSITIVE LOGITS
     FLT
    0.06
    wake
    0.06
    ümüş
    0.06
     Sheep
    0.06
    أن
    0.06
    _DEC
    0.06
    AMPL
    0.06
     awk
    0.05
     واح
    0.05
     anlay
    0.05
    Act Density 0.063%

    No Known Activations