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

    Neuronpedia

    INDEX
    Explanations

    science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orgy
    -0.07
     ammonia
    -0.07
    تعب
    -0.07
     EGL
    -0.07
     сог
    -0.07
     brittle
    -0.06
     picnic
    -0.06
    .Ptr
    -0.06
    未成
    -0.06
    ߦ
    -0.06
    POSITIVE LOGITS
     length
    0.09
    现有的
    0.07
    wy
    0.07
     objective
    0.07
    QUI
    0.07
    [pos
    0.07
    }
↵
↵
↵
↵
    0.07
     including
    0.07
     sender
    0.07
     vector
    0.07
    Act Density 0.006%

    No Known Activations