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

    Neuronpedia

    INDEX
    Explanations

    capitals and administration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Revolution
    -0.07
    下称
    -0.07
     jego
    -0.07
    ascii
    -0.07
    自身的
    -0.07
    posts
    -0.07
    ints
    -0.07
    巨大
    -0.07
    imony
    -0.07
    onto
    -0.07
    POSITIVE LOGITS
    هز
    0.07
    []=$
    0.07
    koń
    0.06
    	L
    0.06
    скор
    0.06
     זקוק
    0.06
    лив
    0.06
    祾
    0.06
    龍
    0.06
    ɛ
    0.06
    Act Density 0.029%

    No Known Activations