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

    Neuronpedia

    INDEX
    Explanations

    references to foreign entities or interactions

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

    foreign followed by categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.66
     jScrollPane
    -0.66
    rungsseite
    -0.66
    KommentareTeilen
    -0.63
    sizeCache
    -0.60
    makeConstraints
    -0.60
     pageContext
    -0.59
    ⟬
    -0.59
    нгред
    -0.59
    ötzlich
    -0.58
    POSITIVE LOGITS
     foreign
    1.03
     Foreign
    0.99
    foreign
    0.92
    FOREIGN
    0.91
     FOREIGN
    0.90
    Foreign
    0.86
     alien
    0.73
     extranjera
    0.68
    <bos>
    0.68
     étrangère
    0.66
    Act Density 0.008%

    No Known Activations