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

    Neuronpedia

    INDEX
    Explanations

    heavy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    טח
    -0.09
    Gesture
    -0.09
    ACE
    -0.08
    ait
    -0.08
     Steiner
    -0.08
     Sty
    -0.08
     potř
    -0.08
    aggia
    -0.07
     Gutschein
    -0.07
    .changed
    -0.07
    POSITIVE LOGITS
    weights
    0.08
     الثقيلة
    0.08
    нод
    0.08
     hitters
    0.07
     Instruments
    0.07
     alph
    0.07
     வாய
    0.07
     instruments
    0.07
     simplesmente
    0.07
     அறிவ
    0.07
    Act Density 0.007%

    No Known Activations