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

    Neuronpedia

    INDEX
    Explanations

    transactions to causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     remise
    0.47
    䐪
    0.43
    НИЕ
    0.43
     اجتما
    0.41
    enziali
    0.41
     கூட்டம்
    0.41
     acompañado
    0.40
     गुरुवार
    0.40
     correto
    0.40
     persönliche
    0.40
    POSITIVE LOGITS
     Epilepsy
    0.57
     Animal
    0.54
     Diabetes
    0.52
     either
    0.51
     Alzheimer
    0.49
    Animal
    0.48
     charity
    0.48
    要么
    0.48
     Cancer
    0.47
    Diabetes
    0.47
    Act Density 0.000%

    No Known Activations