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

    Neuronpedia

    INDEX
    Explanations

    check for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不斷
    0.71
     Svetlana
    0.71
    či
    0.69
     Soa
    0.68
    וב
    0.67
    Чтобы
    0.66
     aşk
    0.66
    Вы
    0.65
     গুরুতর
    0.65
    એસ
    0.65
    POSITIVE LOGITS
     flujo
    0.87
    esercizio
    0.85
    𝘬
    0.82
    isieren
    0.80
    izante
    0.80
     regreso
    0.79
    ions
    0.77
    startsWith
    0.77
    ADO
    0.76
     propres
    0.75
    Act Density 0.000%

    No Known Activations