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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ArgumentOutOfRangeException
    -0.07
    .style
    -0.06
    だから
    -0.06
    之间
    -0.06
     Xml
    -0.06
    doctrine
    -0.06
    renom
    -0.06
    _PANEL
    -0.06
    ائز
    -0.06
    itore
    -0.06
    POSITIVE LOGITS
     common
    0.07
    Cross
    0.06
     Availability
    0.06
    0.06
    	left
    0.06
     contre
    0.06
    ーム
    0.06
    cross
    0.06
    	point
    0.06
    lac
    0.06
    Act Density 0.038%

    No Known Activations