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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sq
    -0.07
    	arg
    -0.06
     usher
    -0.06
     rs
    -0.06
    -decoration
    -0.06
    	os
    -0.06
     thứ
    -0.06
     fatty
    -0.06
    쨍
    -0.06
     Ft
    -0.06
    POSITIVE LOGITS
    (question
    0.08
    样式
    0.07
    instant
    0.07
    _TRIGGER
    0.07
    [counter
    0.07
     wheels
    0.06
     downloading
    0.06
     üret
    0.06
     дем
    0.06
    していない
    0.06
    Act Density 0.009%

    No Known Activations