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

    Neuronpedia

    INDEX
    Explanations

    cyberattacks, Pearl Harbor, attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     algoritmo
    0.45
     bactéries
    0.44
     Bedarf
    0.44
     Künst
    0.42
    专业
    0.42
     മികച്ച
    0.42
     pathophysiology
    0.41
     physiologique
    0.41
     объяс
    0.40
     benutzer
    0.40
    POSITIVE LOGITS
    攻擊
    0.71
     attacks
    0.68
     attacked
    0.67
    attacks
    0.66
    attack
    0.65
     sabotage
    0.65
     vandalism
    0.65
     retali
    0.64
     retaliation
    0.64
     atacar
    0.64
    Act Density 0.082%

    No Known Activations