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

    Neuronpedia

    INDEX
    Explanations

    references to supplementary materials or additional files in a document

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

    additional files or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geografi
    -0.47
    JspWriter
    -0.47
     deuda
    -0.45
     frukt
    -0.42
    inspace
    -0.41
    LabelTagHelper
    -0.41
    setLayoutManager
    -0.41
     Ternyata
    -0.41
    inquirer
    -0.40
     userSchema
    -0.40
    POSITIVE LOGITS
    Additional
    1.63
     Additional
    1.62
    additional
    1.22
    ADDITIONAL
    1.18
     additional
    1.11
     ADDITIONAL
    1.06
    Дополнитель
    0.84
    ditional
    0.79
     Addition
    0.75
     дополнитель
    0.72
    Act Density 0.017%

    No Known Activations