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

    Neuronpedia

    INDEX
    Explanations

    levels and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тоже
    0.46
     olabilir
    0.45
     asemenea
    0.42
     cabeza
    0.41
     bardziej
    0.39
     alguna
    0.39
     tamaño
    0.39
     trecut
    0.39
     иногда
    0.39
    ρεί
    0.38
    POSITIVE LOGITS
     আৰু
    0.41
    International
    0.41
    JOSE
    0.40
    했고
    0.38
     उर्फ
    0.37
     そして
    0.37
     مجبور
    0.36
     Invite
    0.36
    CLR
    0.36
    យើង
    0.35
    Act Density 0.175%

    No Known Activations