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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    累
    -0.07
    คา
    -0.07
    涧
    -0.06
     Cat
    -0.06
    odafone
    -0.06
     icy
    -0.06
    看电视
    -0.06
     Tits
    -0.06
     Leg
    -0.06
    ῶ
    -0.06
    POSITIVE LOGITS
    &R
    0.07
    뉠
    0.07
    המלצות
    0.07
    	renderer
    0.07
    .'/
    0.06
    	pool
    0.06
    웅
    0.06
    錄
    0.06
    point
    0.06
    R
    0.06
    Act Density 0.035%

    No Known Activations