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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stitch
    -0.08
     сай
    -0.07
     patt
    -0.07
     Shopify
    -0.07
     toast
    -0.07
     Stitch
    -0.07
    .sav
    -0.06
    Do
    -0.06
     lawsuit
    -0.06
     اج
    -0.06
    POSITIVE LOGITS
    strategy
    0.06
    Veter
    0.06
    _INS
    0.06
    หม
    0.06
     благ
    0.06
     ConsoleColor
    0.06
    ooter
    0.06
    _groups
    0.06
    řím
    0.06
    __),
    0.06
    Act Density 0.006%

    No Known Activations