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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    요
    -0.07
    돐
    -0.07
    dT
    -0.07
    เศร
    -0.07
    נזק
    -0.07
    告
    -0.07
    的支持
    -0.07
    恧
    -0.07
    oz
    -0.06
    惩罚
    -0.06
    POSITIVE LOGITS
     Redskins
    0.07
     getNode
    0.07
    Emoji
    0.06
     superhero
    0.06
     CVS
    0.06
    {x
    0.06
     экран
    0.06
     kè
    0.06
    𝙭
    0.06
    RegularExpression
    0.06
    Act Density 0.030%

    No Known Activations