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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vortex
    -0.08
     фл
    -0.07
     дух
    -0.07
    腧
    -0.07
     emb
    -0.07
    svm
    -0.07
    主動
    -0.07
    [random
    -0.07
     meld
    -0.07
    MW
    -0.07
    POSITIVE LOGITS
     Saw
    0.08
    俐
    0.07
     sais
    0.07
     ser
    0.07
     "));↵
    0.06
    )}}
    0.06
     Ah
    0.06
     ليس
    0.06
    ))
    0.06
    (exports
    0.06
    Act Density 0.001%

    No Known Activations