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

    Neuronpedia

    INDEX
    Explanations

    object declarations and initializations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necessities
    0.68
    くらいの
    0.62
     contractions
    0.60
     desperate
    0.55
     unprepared
    0.54
     economical
    0.53
     both
    0.53
    plug
    0.52
     SMC
    0.52
    腻
    0.52
    POSITIVE LOGITS
    localObject
    0.73
     oggetti
    0.69
    ächst
    0.68
     回転
    0.68
     Objekt
    0.67
     Objects
    0.66
    ْت
    0.66
     объекта
    0.66
     تھیں
    0.66
     Objekte
    0.66
    Act Density 0.000%

    No Known Activations