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

    Neuronpedia

    INDEX
    Explanations

    fig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToMany
    -0.56
    +:+
    -0.43
    iolis
    -0.43
    idist
    -0.42
     bil
    -0.41
     stocking
    -0.41
    末
    -0.40
     Son
    -0.40
    bes
    -0.39
    isses
    -0.39
    POSITIVE LOGITS
    RegistryLite
    0.84
    lihood
    0.79
    tagHelperRunner
    0.77
     <=",
    0.77
    ArrowToggle
    0.76
     समीक्षाएं
    0.74
     GenerationType
    0.71
    Билгалдахарш
    0.70
    MessageTagHelper
    0.68
     surla
    0.67
    Act Density 0.001%

    No Known Activations