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

    Neuronpedia

    INDEX
    Explanations

    threats and adversaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.45
    水
    0.43
    Impl
    0.42
    mu
    0.42
    abhuto
    0.41
    ホルダー
    0.41
    embryon
    0.41
     Decedent
    0.41
    ṣ
    0.40
    富
    0.40
    POSITIVE LOGITS
     কবল
    0.65
     vanqu
    0.55
     menace
    0.52
     মোকাবি
    0.50
     attacking
    0.47
     threat
    0.46
     menacing
    0.46
     defeated
    0.45
     threats
    0.45
    威胁
    0.43
    Act Density 0.100%

    No Known Activations