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

    Neuronpedia

    INDEX
    Explanations

    GERD

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upgrades
    -0.07
    ónica
    -0.07
    Values
    -0.06
    _Profile
    -0.06
     Opportunity
    -0.06
    .actor
    -0.06
    리아
    -0.06
    所有
    -0.06
     sexism
    -0.06
     prohibit
    -0.06
    POSITIVE LOGITS
     Bind
    0.07
     htmlspecialchars
    0.06
    uld
    0.06
     фот
    0.06
     등을
    0.06
     TIM
    0.06
    Capt
    0.06
    \Events
    0.06
    َي
    0.06
    ičky
    0.06
    Act Density 0.015%

    No Known Activations