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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fon
    -0.07
    ruits
    -0.06
    混
    -0.06
    undos
    -0.06
     Bam
    -0.06
     casos
    -0.06
    صور
    -0.06
    (CancellationToken
    -0.06
     Coat
    -0.06
    ivalence
    -0.06
    POSITIVE LOGITS
    ạ
    0.07
    esseract
    0.07
    imization
    0.06
     assaulting
    0.06
     Vietnamese
    0.06
     slab
    0.06
    Defines
    0.06
    ナー
    0.06
     lok
    0.06
    Đối
    0.06
    Act Density 0.000%

    No Known Activations