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

    Neuronpedia

    INDEX
    Explanations

    Actions that maintain/supply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }}{{
    -0.07
    ORS
    -0.06
    頁
    -0.06
     pancakes
    -0.06
     EDT
    -0.06
    aturdays
    -0.06
    Λ
    -0.06
    Ajax
    -0.06
    ]"
    -0.06
     müzik
    -0.06
    POSITIVE LOGITS
     ринку
    0.06
     مواط
    0.06
     yar
    0.06
    itet
    0.06
    .getM
    0.06
     myš
    0.06
     SECURITY
    0.06
     clave
    0.06
    NJ
    0.06
    vé
    0.06
    Act Density 0.123%

    No Known Activations