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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and qualifiers that express uncertainty or exceptions

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

    if not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     volantes
    -0.50
     Comunicação
    -0.42
     turma
    -0.41
     pouvoit
    -0.41
     kolye
    -0.41
     pinggang
    -0.40
     näin
    -0.40
     Grüsse
    -0.40
     visibilité
    -0.40
     parachoque
    -0.40
    POSITIVE LOGITS
    ResumeLayout
    0.64
     Савезне
    0.62
    хьтан
    0.58
    setVerticalGroup
    0.52
    =")
    0.51
    EndContext
    0.51
    #%%
    0.50
     CreateTagHelper
    0.49
    balleur
    0.48
    "])
    0.48
    Act Density 0.063%

    No Known Activations