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

    Neuronpedia

    INDEX
    Explanations

    minor tweaks to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bezug
    0.46
     شان
    0.42
     પ્રવેશ
    0.42
     Gobierno
    0.42
    但在
    0.41
    分泌
    0.41
    Departamento
    0.41
     bebés
    0.41
    法人
    0.39
     Facultad
    0.39
    POSITIVE LOGITS
    k
    0.50
     firearms
    0.50
     harsher
    0.50
     costing
    0.48
    lications
    0.47
     sqrt
    0.47
     knives
    0.47
    $-
    0.46
     whips
    0.46
    #
    0.46
    Act Density 0.003%

    No Known Activations