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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Audience
    -0.06
    .sf
    -0.06
    ternet
    -0.06
     fft
    -0.06
    _GP
    -0.06
     Speaker
    -0.06
    という
    -0.06
    Td
    -0.06
    .setPositiveButton
    -0.06
     έν
    -0.06
    POSITIVE LOGITS
     $_[
    0.07
    .bias
    0.06
     每
    0.06
     předch
    0.06
     créd
    0.06
     prelim
    0.06
     století
    0.06
     nodo
    0.06
     Honda
    0.06
     Wright
    0.06
    Act Density 0.008%

    No Known Activations