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

    Neuronpedia

    INDEX
    Explanations

    allows prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ériel
    0.41
     JS
    0.41
     GT
    0.39
     ATV
    0.38
    ቲክ
    0.38
    sn
    0.38
    న్నా
    0.38
    sr
    0.38
     komple
    0.38
     установка
    0.37
    POSITIVE LOGITS
     Allows
    0.44
     allows
    0.44
    Allows
    0.44
     diligently
    0.41
     اجازه
    0.40
     diligent
    0.39
    Balancer
    0.38
    allows
    0.38
     industrious
    0.37
     वीजा
    0.37
    Act Density 0.000%

    No Known Activations