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

    Neuronpedia

    INDEX
    Explanations

    Defining terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🏄
    -0.07
     Sign
    -0.07
     дел
    -0.07
    琡
    -0.06
    伴
    -0.06
    namese
    -0.06
    Miss
    -0.06
     Hicks
    -0.06
    .Promise
    -0.06
     création
    -0.06
    POSITIVE LOGITS
    的要求
    0.08
    Ы
    0.08
    га
    0.08
    rics
    0.07
     ülkemiz
    0.07
     هذا
    0.07
    .Est
    0.07
    IZATION
    0.07
     Spencer
    0.07
    ый
    0.06
    Act Density 0.113%

    No Known Activations