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

    Neuronpedia

    INDEX
    Explanations

    Low, Medium, High ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     armies
    0.42
     sekaligus
    0.40
     musculaire
    0.40
     murderous
    0.40
     gigantes
    0.40
     गणित
    0.39
    場合がございます
    0.39
     asimismo
    0.39
     villains
    0.38
     Persians
    0.38
    POSITIVE LOGITS
     सेवा
    0.40
    =
    0.39
    agher
    0.39
    elola
    0.38
    ले
    0.37
    ORN
    0.37
    ZONE
    0.37
    तौर
    0.37
     سے
    0.37
    ্চ
    0.37
    Act Density 0.073%

    No Known Activations