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

    Neuronpedia

    INDEX
    Explanations

    counties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    verständ
    -0.07
    vard
    -0.07
     الغذ
    -0.07
    🏷
    -0.07
     Brenda
    -0.07
     hues
    -0.06
    nm
    -0.06
    	lock
    -0.06
     intox
    -0.06
     SIGN
    -0.06
    POSITIVE LOGITS
    אית
    0.07
    اته
    0.07
     debt
    0.07
    כות
    0.07
    뉜
    0.07
     PartialEq
    0.07
    ット
    0.07
     balanced
    0.07
    的概率
    0.06
    ню
    0.06
    Act Density 0.017%

    No Known Activations