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

    Neuronpedia

    INDEX
    Explanations

    color specifications and formatting in coding or graphical settings

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

    Code snippets or RGBA color values

    np_acts-logits-general · gemini-2.0-flash

    code tokens and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dignité
    -0.75
    devamını
    -0.71
     verità
    -0.66
    enumi
    -0.65
     مشين
    -0.65
     विश्वसनीयता
    -0.65
     vérit
    -0.63
     ouvriers
    -0.62
     dimentic
    -0.62
     termica
    -0.61
    POSITIVE LOGITS
    arschu
    0.54
    ApiModelProperty
    0.48
     internetowa
    0.47
     Penh
    0.46
     berk
    0.45
    Computed
    0.45
     interp
    0.44
    advertisement
    0.44
     hus
    0.44
    curité
    0.43
    Act Density 0.066%

    No Known Activations