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

    Neuronpedia

    INDEX
    Explanations

    attack actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonparametric
    0.44
    ترح
    0.42
     recensement
    0.42
    社會
    0.41
     rulemaking
    0.40
     لکھ
    0.39
     confidentialité
    0.39
    房价
    0.39
     آد
    0.38
    specifiedByURL
    0.38
    POSITIVE LOGITS
     attack
    1.21
     attacks
    1.20
     공격
    1.13
    攻击
    1.12
    攻撃
    1.09
     attacking
    1.05
    攻擊
    1.03
     projectiles
    1.02
     attaques
    1.02
     serangan
    0.98
    Act Density 0.109%

    No Known Activations