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

    Neuronpedia

    INDEX
    Explanations

    isted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compute
    -0.07
     bào
    -0.07
     schl
    -0.07
    兵力
    -0.07
     PRES
    -0.07
    	 ↵
    -0.07
    гор
    -0.07
     split
    -0.06
    SORT
    -0.06
    ury
    -0.06
    POSITIVE LOGITS
     אין
    0.07
    开发者
    0.07
    _icall
    0.07
     distracting
    0.07
    _ip
    0.07
    _numbers
    0.07
     большой
    0.07
     comentário
    0.06
     регистра
    0.06
    就行
    0.06
    Act Density 0.001%

    No Known Activations