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

    Neuronpedia

    INDEX
    Explanations

    references to drugs or smoking behaviors

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

    Ellen, Richard, Canadian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    epam
    -0.42
    ungszeit
    -0.40
    كتوبر
    -0.40
    AddTagHelper
    -0.40
     Herzegovina
    -0.39
    itoare
    -0.38
    ătoare
    -0.38
     kasarigan
    -0.38
     godine
    -0.38
    OGND
    -0.36
    POSITIVE LOGITS
    NameInMap
    0.50
     autorytatywna
    0.46
     raiſ
    0.44
     considérons
    0.43
    ']?>
    0.43
    ngdoc
    0.43
    AutoScaleMode
    0.41
     defaultstate
    0.40
     occaf
    0.39
     classics
    0.35
    Act Density 0.061%

    No Known Activations