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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polo
    -0.07
    Designed
    -0.06
    جم
    -0.06
     obligations
    -0.06
     Hell
    -0.06
    ASHBOARD
    -0.06
    ースト
    -0.06
    Producto
    -0.06
     inventor
    -0.06
     Sing
    -0.06
    POSITIVE LOGITS
    (close
    0.07
    Lorem
    0.06
     prevail
    0.06
     reachable
    0.06
    ,､
    0.06
     могут
    0.06
     может
    0.06
    “↵↵
    0.06
     صنع
    0.06
    otent
    0.06
    Act Density 0.002%

    No Known Activations