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

    Neuronpedia

    INDEX
    Explanations

    code, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pomo
    -0.09
    Gu
    -0.08
     ceva
    -0.08
     પૂ
    -0.08
     બનાવ
    -0.08
     Teng
    -0.08
     biss
    -0.07
    饭
    -0.07
    Hoi
    -0.07
    იის
    -0.07
    POSITIVE LOGITS
    0.08
     instructed
    0.08
    educated
    0.07
     indul
    0.07
    indent
    0.07
     рассмотр
    0.07
     프
    0.07
     '"'
    0.07
     weighed
    0.07
    displaystyle
    0.07
    Act Density 0.315%
    No Known Activations