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

    Neuronpedia

    INDEX
    Explanations

    Off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     যার
    -0.08
     dred
    -0.08
     ملم
    -0.08
    赛
    -0.07
     vyt
    -0.07
     postal
    -0.07
     muse
    -0.07
     শহ
    -0.07
    담
    -0.07
     MATERIAL
    -0.07
    POSITIVE LOGITS
     автоматически
    0.18
     automatisch
    0.18
     automatiquement
    0.17
     automatically
    0.17
    自动
    0.16
     Automatically
    0.16
    Automatically
    0.16
     automáticamente
    0.16
     automatique
    0.16
     자동
    0.16
    Act Density 0.023%

    No Known Activations