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

    Neuronpedia

    INDEX
    Explanations

    protection and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Akt
    0.45
     gostar
    0.42
     offences
    0.42
    你
    0.42
    Votre
    0.42
    人の
    0.42
     aceptación
    0.41
    Yay
    0.41
    屣
    0.41
    Tour
    0.41
    POSITIVE LOGITS
     보호
    0.45
    proven
    0.42
    原有
    0.42
     explains
    0.41
     vald
    0.41
     Multis
    0.41
    保护
    0.41
    ఎం
    0.40
     schützen
    0.40
     সুরক্ষিত
    0.40
    Act Density 0.010%

    No Known Activations