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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /router
    -0.08
     форме
    -0.07
    arning
    -0.06
     fireEvent
    -0.06
    R
    -0.06
     الرو
    -0.06
    .down
    -0.06
    chaft
    -0.06
    Ray
    -0.06
    router
    -0.06
    POSITIVE LOGITS
     Princip
    0.06
    (equalTo
    0.06
     Orb
    0.06
    TickCount
    0.06
     marshal
    0.06
    (MSG
    0.06
    _codes
    0.06
    疾
    0.06
    (StringUtils
    0.06
    /entities
    0.06
    Act Density 0.711%

    No Known Activations