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

    Neuronpedia

    INDEX
    Explanations

    matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Restore
    -0.08
    יפוי
    -0.07
    antiago
    -0.07
    for
    -0.07
    favicon
    -0.07
    �
    -0.07
    Explore
    -0.07
    🍝
    -0.07
    💪
    -0.07
    -terminal
    -0.07
    POSITIVE LOGITS
    农户
    0.07
    ,size
    0.07
     anda
    0.07
     Flat
    0.07
    ёт
    0.06
    >New
    0.06
     لو
    0.06
    Gender
    0.06
    	when
    0.06
     interoper
    0.06
    Act Density 0.008%

    No Known Activations