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

    Neuronpedia

    INDEX
    Explanations

    oothing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilda
    -0.08
    诚信
    -0.07
    ்�
    -0.06
    AND
    -0.06
     personal
    -0.06
    升温
    -0.06
     Tout
    -0.06
    顿
    -0.06
     Xia
    -0.06
     pig
    -0.06
    POSITIVE LOGITS
    RESSED
    0.07
     Immediately
    0.07
    atedRoute
    0.07
     langs
    0.07
    vents
    0.07
    	↵	↵	↵
    0.07
    痛み
    0.07
    されます
    0.07
    ﺙ
    0.07
    	inst
    0.07
    Act Density 0.001%

    No Known Activations