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

    Neuronpedia

    INDEX
    Explanations

    rex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    警示
    -0.08
    般的
    -0.07
     showcasing
    -0.07
     yog
    -0.07
    _REGEX
    -0.07
    焗
    -0.07
    _PR
    -0.07
    -Year
    -0.07
    生态保护
    -0.07
    יצירה
    -0.07
    POSITIVE LOGITS
    앚
    0.08
     ^
    0.07
     spokeswoman
    0.07
    ocup
    0.07
    .map
    0.07
     feel
    0.07
    坽
    0.07
     onUpdate
    0.07
     mediator
    0.07
     darker
    0.07
    Act Density 0.001%

    No Known Activations