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

    Neuronpedia

    INDEX
    Explanations

    code file paths/URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    american
    -0.08
     Champions
    -0.07
    ReadStream
    -0.07
     reverse
    -0.07
     mpg
    -0.06
    timer
    -0.06
    ANGUAGE
    -0.06
     comer
    -0.06
    .initial
    -0.06
    ті
    -0.06
    POSITIVE LOGITS
    ':['
    0.06
    �다
    0.06
     statt
    0.06
     ک
    0.06
    普
    0.06
     вак
    0.06
    odont
    0.06
     newY
    0.06
     Xxx
    0.06
     Wolves
    0.06
    Act Density 0.032%

    No Known Activations