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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and goal setting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     պ
    0.49
    Preis
    0.48
    シリーズ
    0.46
    フランス
    0.44
     ouverture
    0.44
     nedost
    0.44
     spins
    0.44
     empêcher
    0.44
     കരുത
    0.44
     whiche
    0.43
    POSITIVE LOGITS
     Outcome
    0.46
    ayaan
    0.45
    Outcome
    0.44
    arente
    0.43
    acidad
    0.43
     was
    0.43
     Moved
    0.43
     Grants
    0.42
    andingan
    0.41
    Socket
    0.41
    Act Density 0.004%

    No Known Activations