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

    Neuronpedia

    INDEX
    Explanations

    attack and titan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stvu
    0.49
    cdZ
    0.46
    highscore
    0.45
    createUser
    0.43
    contest
    0.43
    創建
    0.42
    hierarchy
    0.42
    gur
    0.41
    adə
    0.41
     އަ
    0.41
    POSITIVE LOGITS
     attack
    0.89
     Attack
    0.85
     attacks
    0.78
     attacking
    0.74
     Attacks
    0.73
     हमला
    0.72
     attaque
    0.70
     assault
    0.67
    Attack
    0.66
     공격
    0.64
    Act Density 0.013%

    No Known Activations