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

    Neuronpedia

    INDEX
    Explanations

    meant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฆ
    -0.07
    背上
    -0.07
    洋葱
    -0.07
    iosis
    -0.07
     become
    -0.07
    פר
    -0.07
    ifact
    -0.07
     dis
    -0.07
     abandon
    -0.07
    "><!--
    -0.07
    POSITIVE LOGITS
     meant
    0.09
    .gca
    0.07
     значения
    0.07
    מעצב
    0.07
     ראוי
    0.06
    textBox
    0.06
    𝖒
    0.06
     createContext
    0.06
    	u
    0.06
    тр
    0.06
    Act Density 0.007%

    No Known Activations