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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating questions or uncertainty

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

    slaves, black, do, foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étrangers
    -0.36
    addGroup
    -0.35
    انتهای
    -0.34
     gekomen
    -0.33
    StructEnd
    -0.32
     veiks
    -0.32
     gärna
    -0.32
     tocó
    -0.32
    teil
    -0.31
     căr
    -0.31
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.64
    AsUp
    0.63
    transQ
    0.60
    sonaro
    0.54
    存于互联网档案馆
    0.54
    RegressionTest
    0.52
    tagHelperRunner
    0.48
    AsStream
    0.48
    idelberg
    0.48
     santiago
    0.47
    Act Density 0.122%

    No Known Activations