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

    Neuronpedia

    INDEX
    Explanations

    numbers in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     benefits
    -0.07
    并购
    -0.07
     tie
    -0.07
    快樂
    -0.07
     formData
    -0.07
    readonly
    -0.07
    Disclosure
    -0.06
    akhir
    -0.06
     pouch
    -0.06
    kg
    -0.06
    POSITIVE LOGITS
     epis
    0.07
     capit
    0.06
    trees
    0.06
    𝚠
    0.06
     intervened
    0.06
    (interface
    0.06
    (iterator
    0.06
    Depart
    0.06
     WEST
    0.06
    /el
    0.06
    Act Density 0.042%

    No Known Activations