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

    Neuronpedia

    INDEX
    Explanations

    among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isdir
    0.38
    आपका
    0.35
    淫
    0.34
    acer
    0.33
     Typical
    0.33
     précédemment
    0.33
     забе
    0.32
    锤
    0.32
     டன்
    0.32
    istor
    0.32
    POSITIVE LOGITS
     among
    1.25
     wśród
    1.16
     среди
    1.10
     amongst
    1.06
     Among
    1.03
    among
    1.02
    Among
    1.02
     blandt
    1.02
     među
    0.93
     kalangan
    0.90
    Act Density 0.022%

    No Known Activations