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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     znal
    -0.07
     Fs
    -0.07
    ísto
    -0.06
    ()))↵
    -0.06
    ultan
    -0.06
    )>=
    -0.06
    bern
    -0.06
    "));↵
    -0.06
     Ful
    -0.06
    	cf
    -0.06
    POSITIVE LOGITS
    schema
    0.07
    Κ
    0.07
    Ui
    0.06
     Shortcut
    0.06
     Comparison
    0.06
     naše
    0.06
     yorum
    0.06
    Characters
    0.06
     نظر
    0.06
    を作
    0.06
    Act Density 0.000%

    No Known Activations