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

    Neuronpedia

    INDEX
    Explanations

    percentages expressed in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URLs with percent encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infór
    -0.45
    InstanceState
    -0.43
     tiroirs
    -0.42
     ActivatedRoute
    -0.42
     ruinas
    -0.41
    śnia
    -0.41
     reducido
    -0.41
     Ucrania
    -0.41
    Unfinished
    -0.40
    utuhkan
    -0.40
    POSITIVE LOGITS
    %
    0.69
     didst
    0.56
    {%
    0.54
    tagPool
    0.54
     ***!
    0.53
    %")
    0.52
     '%'
    0.52
     Chr
    0.52
    %\
    0.51
    %%%%%
    0.51
    Act Density 0.007%

    No Known Activations