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

    Neuronpedia

    INDEX
    Explanations

    start of code or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aconte
    0.45
     cuya
    0.43
    வ்வ
    0.43
    agel
    0.43
     cohes
    0.42
    르는
    0.42
    اث
    0.41
    touches
    0.41
     çeşit
    0.41
     infección
    0.40
    POSITIVE LOGITS
    埤
    0.46
    ifferent
    0.46
     ഇത്തരം
    0.46
     determined
    0.46
    渎
    0.45
    '
    0.44
    ITO
    0.44
     ära
    0.43
    </a>
    0.43
    鲐
    0.43
    Act Density 0.000%

    No Known Activations