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

    Neuronpedia

    INDEX
    Explanations

    percentages describing family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⊰
    -0.08
     smugg
    -0.08
    udoku
    -0.07
    .choose
    -0.06
     пс
    -0.06
    谎
    -0.06
    缦
    -0.06
    _override
    -0.06
    محا
    -0.06
    🎐
    -0.06
    POSITIVE LOGITS
     있을
    0.07
     Titan
    0.07
     interests
    0.07
    IDs
    0.07
    (title
    0.07
    угл
    0.07
     luật
    0.07
     הגבוה
    0.07
    ceipt
    0.07
     stained
    0.07
    Act Density 0.006%

    No Known Activations