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

    Neuronpedia

    INDEX
    Explanations

    Code snippets using RDD

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     child
    -0.07
     "('
    -0.07
    ptime
    -0.07
     Child
    -0.06
     بسیاری
    -0.06
    ewear
    -0.06
     Guests
    -0.06
    禮
    -0.06
     Sheet
    -0.06
    	buff
    -0.06
    POSITIVE LOGITS
    	select
    0.06
    roat
    0.06
    .Tick
    0.06
     lifestyles
    0.06
     جامع
    0.06
    (ff
    0.06
    tür
    0.06
    .richTextBox
    0.06
    .struct
    0.06
     تولید
    0.06
    Act Density 0.015%

    No Known Activations