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

    Neuronpedia

    INDEX
    Explanations

    definitions and word usage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hello
    -0.07
    ᒌ
    -0.07
    坡
    -0.07
    celain
    -0.06
    isoft
    -0.06
    时隔
    -0.06
    ceu
    -0.06
    时间为
    -0.06
     success
    -0.06
    Mi
    -0.06
    POSITIVE LOGITS
    _community
    0.07
    zend
    0.07
    _Parameter
    0.07
    embr
    0.07
     mn
    0.07
     terminals
    0.07
    	st
    0.07
    internal
    0.07
    Int
    0.07
    etest
    0.07
    Act Density 0.046%

    No Known Activations