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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibern
    -0.07
    Sell
    -0.07
    .MM
    -0.07
    -mm
    -0.07
     sell
    -0.07
     killers
    -0.07
     candidate
    -0.07
     Sell
    -0.07
    -flow
    -0.07
    ुव
    -0.07
    POSITIVE LOGITS
     __________________
    0.08
     lavender
    0.08
     দী
    0.08
     wallpaper
    0.08
    ībā
    0.08
     নাট
    0.08
    ა�
    0.08
     validar
    0.08
    CLS
    0.08
     ഇന്ത്യൻ
    0.08
    Act Density 0.347%

    No Known Activations