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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	filename
    -0.07
    �
    -0.07
    cross
    -0.07
    阳性
    -0.07
    放眼
    -0.07
    흑
    -0.06
    	DD
    -0.06
     MATLAB
    -0.06
    旅馆
    -0.06
    了好几
    -0.06
    POSITIVE LOGITS
    érieur
    0.08
    aybe
    0.08
     Generating
    0.08
    ably
    0.07
     purge
    0.07
     الأخرى
    0.06
    hões
    0.06
    ủy
    0.06
    之間
    0.06
    _r
    0.06
    Act Density 0.006%

    No Known Activations