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

    Neuronpedia

    INDEX
    Explanations

    horsepower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prohibited
    -0.08
    odian
    -0.08
     convol
    -0.08
     migraine
    -0.08
     विज्ञान
    -0.08
    ond
    -0.07
     protesters
    -0.07
     Aboriginal
    -0.07
     vertra
    -0.07
     represents
    -0.07
    POSITIVE LOGITS
     horsepower
    0.09
     engines
    0.09
    .Host
    0.09
     sied
    0.08
     Ceiling
    0.08
    .ly
    0.08
     влад
    0.08
    .Port
    0.08
     seats
    0.08
     Seats
    0.08
    Act Density 0.003%

    No Known Activations