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

    Neuronpedia

    INDEX
    Explanations

    programming, finance, and health topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    henius
    0.39
    賑
    0.39
     (!)
    0.38
     recuperar
    0.38
    จัดการ
    0.38
     credo
    0.38
     hashMap
    0.38
     begrü
    0.38
     হজযাত্র
    0.37
     Drying
    0.37
    POSITIVE LOGITS
     ಮಾಡ
    0.40
    ma
    0.37
     ප
    0.36
    condition
    0.36
    barrier
    0.36
     olun
    0.36
    scaling
    0.35
     совмести
    0.35
     impossible
    0.35
     Министерство
    0.35
    Act Density 0.000%

    No Known Activations