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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of exclusion

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

    neither nor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \}\
    -0.37
     нового
    -0.35
    Примітки
    -0.35
    ísticas
    -0.35
    mybatisplus
    -0.35
    vcut
    -0.34
    >-->
    -0.34
    اتها
    -0.34
    ]=='
    -0.34
    ️
    -0.34
    POSITIVE LOGITS
     neither
    0.80
    Neither
    0.79
     Neither
    0.79
     nor
    0.78
     siquiera
    0.74
    neither
    0.73
     ni
    0.69
     nemmeno
    0.64
    ύτε
    0.62
    Nor
    0.61
    Act Density 0.010%

    No Known Activations