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

    Neuronpedia

    INDEX
    Explanations

    start of turn or PlantUML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    íst
    0.39
     যখন
    0.39
    점에
    0.38
    rospection
    0.38
    瑛
    0.38
    鄢
    0.38
     ورځې
    0.38
     dom
    0.37
     scr
    0.37
     도시
    0.37
    POSITIVE LOGITS
     मुहिम
    0.41
    Chief
    0.39
     existência
    0.38
     chief
    0.38
     ஊற
    0.38
    Infer
    0.37
    Pick
    0.36
    Charges
    0.36
     trabajo
    0.36
    structed
    0.36
    Act Density 0.005%

    No Known Activations