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

    Neuronpedia

    INDEX
    Explanations

    Tony

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۴
    -0.07
     eight
    -0.07
    ид
    -0.07
    üs
    -0.07
    <_
    -0.07
     roofing
    -0.06
     four
    -0.06
     quadrant
    -0.06
     toward
    -0.06
     Yemen
    -0.06
    POSITIVE LOGITS
    (open
    0.07
    染
    0.07
    __('
    0.06
    =l
    0.06
    _SOURCE
    0.06
     protagon
    0.06
    一直
    0.06
    (substr
    0.06
    镜
    0.06
    (def
    0.06
    Act Density 0.001%

    No Known Activations