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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Она
    -0.06
     unab
    -0.06
    zeň
    -0.06
    Пр
    -0.06
    Wait
    -0.06
     weighs
    -0.06
     Funding
    -0.06
    兩
    -0.06
    enor
    -0.06
     Yük
    -0.06
    POSITIVE LOGITS
    ación
    0.07
     аром
    0.06
    stal
    0.06
    -script
    0.06
    -N
    0.06
    主义
    0.06
    Lemma
    0.06
     betray
    0.06
    >manual
    0.06
     Lemma
    0.06
    Act Density 0.047%

    No Known Activations