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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Section
    -0.07
     smokers
    -0.07
    وغ
    -0.07
    plane
    -0.07
    _pdf
    -0.06
    dir
    -0.06
     planes
    -0.06
    -layer
    -0.06
    OG
    -0.06
     react
    -0.06
    POSITIVE LOGITS
     черв
    0.06
     січня
    0.06
     regulator
    0.06
     ἐ
    0.06
     IKE
    0.06
    .setStyleSheet
    0.06
     최고
    0.06
    /gcc
    0.06
     rewritten
    0.06
    После
    0.06
    Act Density 0.006%

    No Known Activations