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

    Neuronpedia

    INDEX
    Explanations

    references to dietary and health management practices

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

    drinking water, well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arrêter
    -0.45
     betweenstory
    -0.42
    ükemmel
    -0.42
     themselves
    -0.39
     sjø
    -0.37
    adaptiveStyles
    -0.37
     jefes
    -0.36
    empêcher
    -0.36
     compañero
    -0.35
     ospiti
    -0.35
    POSITIVE LOGITS
    UnusedPrivate
    0.55
    mployment
    0.53
    simpleType
    0.51
    AutoScaleMode
    0.50
     مرئيه
    0.50
     ویکی‌پدی
    0.49
     informée
    0.47
     مشين
    0.47
    XtraBars
    0.47
    Recomend
    0.46
    Act Density 0.008%

    No Known Activations