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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    werp
    -0.06
    journal
    -0.06
    щими
    -0.06
     injured
    -0.06
     nuest
    -0.06
     tất
    -0.06
    prech
    -0.06
    hledem
    -0.06
    Bucket
    -0.06
    åde
    -0.06
    POSITIVE LOGITS
    732
    0.07
     não
    0.07
    /********************************************************
    0.06
    ably
    0.06
     horribly
    0.06
     Merr
    0.06
    TL
    0.06
     stalled
    0.06
     che
    0.06
    :
↵
    0.06
    Act Density 0.151%

    No Known Activations