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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     industries
    -0.07
     الأن
    -0.07
     просто
    -0.07
    δας
    -0.07
    знача
    -0.07
     عشر
    -0.06
    abby
    -0.06
    “No
    -0.06
    boru
    -0.06
    ยาย
    -0.06
    POSITIVE LOGITS
     Fry
    0.07
     pubkey
    0.07
     hinder
    0.06
    /icon
    0.06
     博
    0.06
     setObject
    0.06
    .getProject
    0.06
     frying
    0.06
     Dyn
    0.06
    .setToolTip
    0.06
    Act Density 0.053%

    No Known Activations