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

    Neuronpedia

    INDEX
    Explanations

    aging or attack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attack
    -1.06
     Attack
    -0.91
    attack
    -0.91
    Attack
    -0.82
     يتيمه
    -0.79
     attacked
    -0.72
     ataque
    -0.71
     ATTACK
    -0.70
     attaque
    -0.68
    ConstraintMaker
    -0.66
    POSITIVE LOGITS
     distractions
    0.66
    æl
    0.60
     distraction
    0.59
     mysteries
    0.59
     cancellations
    0.57
     controversies
    0.56
     drills
    0.56
     Inquiries
    0.56
     accidents
    0.56
    nthetic
    0.56
    Act Density 0.124%

    No Known Activations