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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sz
    -0.07
     Mug
    -0.07
    ejte
    -0.06
    IPS
    -0.06
    JNIEnv
    -0.06
    getState
    -0.06
    	writel
    -0.06
     پاک
    -0.06
    (_("
    -0.06
    _sizes
    -0.06
    POSITIVE LOGITS
     climate
    0.08
    ψει
    0.08
     Ann
    0.07
     fitness
    0.07
     welcome
    0.06
     ++)
    0.06
     predicted
    0.06
     ai
    0.06
    跳
    0.06
    Climate
    0.06
    Act Density 0.005%

    No Known Activations