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

    Neuronpedia

    INDEX
    Explanations

    offensive strategies and force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ל
    0.87
    ن
    0.82
    ل
    0.71
    م
    0.71
    س
    0.66
    מ
    0.61
    с
    0.60
    رو
    0.59
    ك
    0.59
    し
    0.58
    POSITIVE LOGITS
    ’
    0.55
    ,
    0.49
    ated
    0.45
     musical
    0.44
     Springsteen
    0.43
     Scotty
    0.43
    )’
    0.42
     animal
    0.41
    ,’
    0.40
    )?
    0.40
    Act Density 0.001%

    No Known Activations