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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lenker
    -0.88
    AxisAlignment
    -0.82
    ImageContext
    -0.81
    VideoCapture
    -0.77
    tagHelperRunner
    -0.75
    StoryboardSegue
    -0.75
    ſelf
    -0.73
    AddTagHelper
    -0.73
    脚注の使い方
    -0.73
    DrawerToggle
    -0.72
    POSITIVE LOGITS
    .
    0.68
    ,
    0.60
     because
    0.52
    !
    0.51
    ...
    0.47
    !!
    0.45
    …
    0.45
     especially
    0.44
    —
    0.44
    --
    0.43
    Act Density 0.000%

    No Known Activations