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

    Neuronpedia

    INDEX
    Explanations

    responsibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     receptors
    0.50
     restaurants
    0.46
    ulaires
    0.46
     contests
    0.45
     claims
    0.45
    Volvo
    0.44
     preven
    0.44
     alleges
    0.43
     welcomes
    0.42
    성에
    0.42
    POSITIVE LOGITS
    لت
    0.52
    Ⅺ
    0.48
    ды
    0.47
    ⼒
    0.47
     चरणों
    0.47
    жи
    0.46
    менно
    0.46
    ⾯
    0.46
    хождения
    0.45
    зи
    0.45
    Act Density 0.000%

    No Known Activations