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
     voyeur
    -0.09
    онс
    -0.09
    �
    -0.08
     दूसरे
    -0.08
    CASE
    -0.08
     Theft
    -0.08
     сосед
    -0.08
     consultations
    -0.08
    itrust
    -0.08
     theft
    -0.08
    POSITIVE LOGITS
     Aussage
    0.08
     quickly
    0.08
     rapidamente
    0.08
     keywords
    0.08
     snabbt
    0.08
     快
    0.08
     rápidamente
    0.08
     schnelle
    0.07
     schnell
    0.07
     swiftly
    0.07
    Act Density 0.008%

    No Known Activations