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

    Neuronpedia

    INDEX
    Explanations

    hand and subsequent action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iagnosed
    0.48
    λούν
    0.47
    োলন
    0.41
    قيق
    0.40
    詁
    0.40
     शार
    0.38
    ανα
    0.38
    瀕
    0.38
    terminology
    0.37
     viêm
    0.37
    POSITIVE LOGITS
    رسی
    0.52
     بسته
    0.47
     Malk
    0.45
     band
    0.44
    iala
    0.43
     बांध
    0.43
    band
    0.42
    bind
    0.41
    گیر
    0.41
     اندر
    0.41
    Act Density 0.000%

    No Known Activations