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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    方案
    -0.06
    (lambda
    -0.06
     encompasses
    -0.06
     Kota
    -0.06
    (stack
    -0.06
     swollen
    -0.06
    	catch
    -0.06
    (xs
    -0.06
    ambda
    -0.06
    _spinner
    -0.06
    POSITIVE LOGITS
    女
    0.07
    排
    0.07
    .descripcion
    0.06
    (MethodImplOptions
    0.06
    _sort
    0.06
    /screen
    0.06
    �
    0.06
    鏡
    0.06
    '"↵
    0.06
     jam
    0.06
    Act Density 0.000%

    No Known Activations