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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ِه
    -0.06
    olf
    -0.06
     Renaissance
    -0.06
    IVO
    -0.06
    保護
    -0.06
    ідно
    -0.06
    وجود
    -0.06
     Ideal
    -0.06
    shipping
    -0.05
    مع
    -0.05
    POSITIVE LOGITS
     ()↵↵
    0.07
    	Transform
    0.06
     willing
    0.06
    _lm
    0.06
     promised
    0.06
    ListBox
    0.06
    aneously
    0.06
     millis
    0.06
    Duplicates
    0.06
    artial
    0.06
    Act Density 0.004%

    No Known Activations