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
    upaten
    0.38
    ILABLE
    0.36
    ctype
    0.35
    කට
    0.34
     insanın
    0.34
    하시오
    0.34
    ালি
    0.33
    হ্যা
    0.33
    uições
    0.32
     ఎన్ని
    0.32
    POSITIVE LOGITS
     among
    4.19
    among
    3.67
     среди
    3.61
     Among
    3.59
     amongst
    3.58
     wśród
    3.44
    Among
    3.41
     parmi
    3.25
     blandt
    3.05
     Amongst
    2.97
    Act Density 0.071%

    No Known Activations