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

    Neuronpedia

    INDEX
    Explanations

    AI and intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mythical
    -0.08
     Constr
    -0.07
    _TEM
    -0.07
    iro
    -0.07
    WOOD
    -0.06
    .body
    -0.06
    енного
    -0.06
     RW
    -0.06
    Prefab
    -0.06
     ж
    -0.06
    POSITIVE LOGITS
     леч
    0.07
    Executing
    0.07
     أص
    0.07
     Πανεπ
    0.07
    _stylesheet
    0.06
    _frequency
    0.06
     setattr
    0.06
     handleError
    0.06
    ерь
    0.06
     varsa
    0.06
    Act Density 0.063%

    No Known Activations