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

    Neuronpedia

    INDEX
    Explanations

    focus group discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilience
    0.45
    ترین
    0.43
    ونة
    0.43
     sensibil
    0.43
    concurrent
    0.42
     inici
    0.42
    いっぱい
    0.42
    inkl
    0.42
    ین
    0.41
    інки
    0.41
    POSITIVE LOGITS
     t
    0.43
     இனி
    0.42
     loosened
    0.41
     kneel
    0.41
    」、
    0.40
     nếu
    0.40
     সরে
    0.39
     replace
    0.39
     U
    0.38
     brochures
    0.38
    Act Density 0.004%

    No Known Activations