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

    Neuronpedia

    INDEX
    Explanations

    representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     satisfactory
    -0.07
     conven
    -0.07
    uro
    -0.07
     unfavorable
    -0.06
    JAVA
    -0.06
    腾
    -0.06
    地中海
    -0.06
    جي
    -0.06
    ConfigurationException
    -0.06
     الحكم
    -0.06
    POSITIVE LOGITS
    冕
    0.08
    -interface
    0.07
    pb
    0.07
    tier
    0.07
     tarn
    0.07
    𝓃
    0.07
     nailed
    0.07
    -archive
    0.07
    _SIMPLE
    0.07
     Hexatrigesimal
    0.07
    Act Density 0.007%

    No Known Activations