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

    Neuronpedia

    INDEX
    Explanations

    references to personal controversies and allegations involving individuals

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

    foreign allegations and claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emphas
    -0.38
     emphasised
    -0.33
     emphasizes
    -0.32
    GOTREF
    -0.32
    Tre
    -0.32
     emphasise
    -0.32
     Tre
    -0.31
    オス
    -0.31
    GRESS
    -0.31
    usleep
    -0.30
    POSITIVE LOGITS
    ########.
    0.71
    +#+#
    0.69
    Дереккөздер
    0.65
    Хьажоргаш
    0.60
     Photocase
    0.59
     angeb
    0.59
     ब्रेकडाउन
    0.56
    جغرافيا
    0.56
     Савезне
    0.56
    ⟬
    0.55
    Act Density 0.036%

    No Known Activations