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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.64
     (
    0.61
     S
    0.60
     involves
    0.60
     sk
    0.60
     chaos
    0.59
     brittle
    0.58
     vs
    0.58
     and
    0.57
    (
    0.57
    POSITIVE LOGITS
     !***
    1.04
    :])
    1.04
     ***!
    1.02
    ',)
    1.02
    ,</
    1.01
    ,))
    1.01
    :""
    1.01
     '.</
    1.01
    :')
    1.00
     ').
    0.98
    Act Density 0.997%

    No Known Activations