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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tile
    -0.07
    全国
    -0.07
     freeway
    -0.06
     Boss
    -0.06
     KUR
    -0.06
    -alone
    -0.06
    FK
    -0.06
    calcul
    -0.06
    Storyboard
    -0.06
     Rate
    -0.06
    POSITIVE LOGITS
    openh
    0.07
    επ
    0.07
    igator
    0.07
    нолог
    0.06
     Россий
    0.06
    NK
    0.06
    <Rigidbody
    0.06
    .engine
    0.06
     för
    0.06
     gerade
    0.06
    Act Density 0.073%

    No Known Activations