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

    Neuronpedia

    INDEX
    Explanations

    mentions of annotations or metadata in the form of "@" symbols

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

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.41
     saja
    -0.32
    TacToe
    -0.31
    inSlope
    -0.29
     saco
    -0.28
    istream
    -0.28
    îtra
    -0.28
     插图
    -0.28
     possesso
    -0.28
    -)
    -0.27
    POSITIVE LOGITS
     @
    1.95
     (@
    1.13
    .@
    1.05
    =@
    1.05
    (@
    1.05
     @_
    1.02
    ,@
    0.98
    /@
    0.97
     @$
    0.95
     [@
    0.92
    Act Density 0.078%

    No Known Activations