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
     эф
    -0.07
    -part
    -0.07
    -qu
    -0.06
    _black
    -0.06
    -ie
    -0.06
     dotted
    -0.06
    ßer
    -0.06
    ानस
    -0.06
     erh
    -0.06
     Sy
    -0.06
    POSITIVE LOGITS
     Conditional
    0.07
     Milwaukee
    0.06
    etcode
    0.06
     blockSize
    0.06
    Ticket
    0.06
     ora
    0.06
    rouw
    0.06
     Ston
    0.06
     then
    0.06
    .Char
    0.06
    Act Density 0.000%

    No Known Activations