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

    Neuronpedia

    INDEX
    Explanations

    employee relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.93
    mem
    0.79
    mirror
    0.74
     কিনা
    0.73
     verwenden
    0.73
    srt
    0.72
    hyp
    0.72
    pe
    0.71
    yu
    0.71
    e
    0.70
    POSITIVE LOGITS
     dwind
    0.84
    )}}{\
    0.84
     precincts
    0.82
    ুস
    0.79
     forefathers
    0.79
     vostre
    0.78
     ନ
    0.77
     bâtiments
    0.77
     roared
    0.77
     parishioners
    0.77
    Act Density 0.001%

    No Known Activations