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

    Neuronpedia

    INDEX
    Explanations

    Group Policy Objects (GPO)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bij
    -0.09
    क्राउ
    -0.09
    的钱
    -0.09
     Projectile
    -0.09
     displaced
    -0.09
     monedas
    -0.09
     ventures
    -0.09
     আহত
    -0.09
    _stride
    -0.09
     घायल
    -0.08
    POSITIVE LOGITS
     directives
    0.10
     overrides
    0.10
    設定
    0.10
     설정
    0.09
     настройки
    0.09
    Overrides
    0.09
     lockdown
    0.09
     override
    0.09
     checklist
    0.09
     Einstellungen
    0.09
    Act Density 0.005%

    No Known Activations