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

    Neuronpedia

    INDEX
    Explanations

    js

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubb
    -0.08
    هو
    -0.08
     fucked
    -0.07
    挛
    -0.07
    Yep
    -0.07
    谋
    -0.06
    umbo
    -0.06
    吵
    -0.06
    背包
    -0.06
    embrance
    -0.06
    POSITIVE LOGITS
    0.07
     halten
    0.07
    .res
    0.06
     StringUtil
    0.06
     objects
    0.06
    .Pre
    0.06
    陰
    0.06
     DT
    0.06
    )?$
    0.06
    PointSize
    0.06
    Act Density 0.005%

    No Known Activations