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

    Neuronpedia

    INDEX
    Explanations

    gap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marched
    -0.08
     בספר
    -0.07
     accumulation
    -0.07
    随处可见
    -0.07
    荏
    -0.07
    企业提供
    -0.07
    ᚌ
    -0.07
    _command
    -0.07
    只需
    -0.07
    intptr
    -0.07
    POSITIVE LOGITS
    LOW
    0.07
     Insights
    0.07
    Anal
    0.07
    逼近
    0.07
    昂
    0.07
    ᨲ
    0.07
    ULATE
    0.06
    Analysis
    0.06
    -delay
    0.06
    UTURE
    0.06
    Act Density 0.004%

    No Known Activations