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

    Neuronpedia

    INDEX
    Explanations

    placeholders and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </li>
    0.66
     exemple
    0.63
    ুগত্য
    0.62
    )^*
    0.62
    </a>
    0.61
     bijvoorbeeld
    0.61
     exemplo
    0.59
     kanske
    0.59
     zarar
    0.59
    </span>
    0.58
    POSITIVE LOGITS
    مدينة
    0.71
    green
    0.65
    sack
    0.63
    erté
    0.61
    Name
    0.61
    Type
    0.61
    atype
    0.60
    jenigen
    0.60
    ersk
    0.60
    goo
    0.59
    Act Density 0.190%

    No Known Activations