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

    Neuronpedia

    INDEX
    Explanations

    terms related to analysis or comparison in data contexts

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

    describing outcomes and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geographically
    -0.41
     colonie
    -0.40
     république
    -0.38
     colonial
    -0.37
     anſ
    -0.36
     libremente
    -0.36
     vapa
    -0.36
    estero
    -0.36
     raggiunto
    -0.36
    delen
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.65
    SequentialGroup
    0.60
     الرياضيه
    0.57
     nakalista
    0.54
     ligiloj
    0.54
    intios
    0.51
    richTextPanel
    0.51
    tagHelperRunner
    0.51
     kasarigan
    0.51
     TextAlign
    0.51
    Act Density 0.000%

    No Known Activations