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

    Neuronpedia

    INDEX
    Explanations

    LaTeX and mathematical symbols used in equations

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

    LaTeX or HTML formatting tags usage

    np_acts-logits-general · gemini-2.0-flash

    latex markup and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.99
     estekak
    -0.98
    脚注の使い方
    -0.94
     HasFactory
    -0.91
    expandindo
    -0.88
    ſelves
    -0.88
    PerformLayout
    -0.86
     AssemblyCulture
    -0.85
    Šaltiniai
    -0.84
    ValueGeneration
    -0.83
    POSITIVE LOGITS
    CJK
    1.38
    textbackslash
    0.56
    EMPL
    0.55
     and
    0.54
     the
    0.54
    ggplot
    0.54
     a
    0.52
    ,
    0.52
     Ellison
    0.51
     (
    0.51
    Act Density 0.057%

    No Known Activations