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

    Neuronpedia

    INDEX
    Explanations

    protection mechanisms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Particular
    -0.09
    在哪里
    -0.09
     dónde
    -0.09
     Extended
    -0.09
    ónde
    -0.09
    在哪
    -0.08
     nuance
    -0.08
     ironing
    -0.08
     Rencontre
    -0.08
    來源
    -0.08
    POSITIVE LOGITS
     guardians
    0.10
    Protect
    0.09
     защиты
    0.09
     labyrinth
    0.09
     활성
    0.09
     protective
    0.09
     protección
    0.09
     unleashed
    0.09
     aktiviert
    0.09
     mechanisms
    0.09
    Act Density 0.023%

    No Known Activations