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

    Neuronpedia

    INDEX
    Explanations

    dates and lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENDER
    -0.07
     columnName
    -0.07
     Tender
    -0.07
    我想
    -0.07
    小姑娘
    -0.07
    مت
    -0.06
     EXEC
    -0.06
    uppe
    -0.06
    北大
    -0.06
     Narrative
    -0.06
    POSITIVE LOGITS
    掩
    0.07
     coastal
    0.07
     =================================================
    0.07
     Conditional
    0.07
    뷸
    0.06
    뀐
    0.06
    Chain
    0.06
    寫
    0.06
    antis
    0.06
    (hist
    0.06
    Act Density 0.142%

    No Known Activations