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
    tbl
    -0.07
     loop
    -0.07
    bundle
    -0.07
    육
    -0.07
     inspection
    -0.07
     ayrıl
    -0.06
     Pick
    -0.06
    until
    -0.06
    滾
    -0.06
    ===========
    -0.06
    POSITIVE LOGITS
    ↵↵↵
    0.07
    ↵↵↵↵↵
    0.07
    десят
    0.06
    恰
    0.06
    背后
    0.06
    ;
↵
↵
    0.06
    malink
    0.06
     شخص
    0.06
    ression
    0.06
    မ
    0.06
    Act Density 0.125%

    No Known Activations