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

    Neuronpedia

    INDEX
    Explanations

    user interface elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Button
    -1.02
     flavor
    -1.00
    flavor
    -0.97
     BUTTON
    -0.96
     button
    -0.95
     Flavor
    -0.95
    Button
    -0.90
    button
    -0.90
     flavour
    -0.86
     botão
    -0.83
    POSITIVE LOGITS
    ing
    0.80
    ING
    0.61
    izing
    0.55
    less
    0.53
     impact
    0.52
    ViewFeatures
    0.48
    تقاوى
    0.47
    rous
    0.46
    ed
    0.46
    ued
    0.45
    Act Density 0.078%

    No Known Activations