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

    Neuronpedia

    INDEX
    Explanations

    iam

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Air
    -0.07
    Camb
    -0.07
    ác
    -0.07
     eaten
    -0.06
     Math
    -0.06
    Math
    -0.06
     unfairly
    -0.06
    Documentation
    -0.06
    飔
    -0.06
     child
    -0.06
    POSITIVE LOGITS
    𝙻
    0.07
    枣庄
    0.07
    缩减
    0.07
     siege
    0.07
    根源
    0.07
    庞大的
    0.07
    קטע
    0.07
    几次
    0.07
    悠久
    0.07
    "];↵
    0.07
    Act Density 0.000%

    No Known Activations