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

    Neuronpedia

    INDEX
    Explanations

    recalling past statements / "you mentioned"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.65
     ഉയർന്ന
    0.62
    japan
    0.62
     ショルダー
    0.62
     muszą
    0.62
     자동차
    0.60
     who
    0.58
     fastener
    0.58
     ಮುಂದ
    0.58
    apayati
    0.58
    POSITIVE LOGITS
    ور
    0.75
    ين
    0.63
    وة
    0.61
    وڑ
    0.60
    м
    0.59
    ط
    0.59
    )
    0.57
     soldados
    0.56
    чик
    0.56
    ስት
    0.55
    Act Density 0.000%

    No Known Activations