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

    Neuronpedia

    INDEX
    Explanations

    German

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    finalize
    -0.07
     freel
    -0.07
     decades
    -0.07
    	false
    -0.07
    晖
    -0.07
    <File
    -0.07
     deterior
    -0.07
     ik
    -0.06
    -xs
    -0.06
    	buf
    -0.06
    POSITIVE LOGITS
     אחי
    0.07
    ていきます
    0.07
     especialmente
    0.07
    resses
    0.06
    /categories
    0.06
     LOVE
    0.06
     międ
    0.06
    ⚭
    0.06
    ✭
    0.06
    منظومة
    0.06
    Act Density 0.024%

    No Known Activations