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

    Neuronpedia

    INDEX
    Explanations

    leche entera, tazón

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ǥ
    0.44
     effectively
    0.41
    फाली
    0.41
    ϻ
    0.41
     mago
    0.41
    ধ্যার
    0.40
     gevonden
    0.40
     Effectively
    0.39
    في
    0.39
    вати
    0.39
    POSITIVE LOGITS
    ills
    0.38
     bonnes
    0.38
    oglou
    0.35
    сыз
    0.35
    ikka
    0.34
    ックレス
    0.34
    olda
    0.34
    secs
    0.33
     ONE
    0.33
     WOR
    0.33
    Act Density 0.000%

    No Known Activations