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

    Neuronpedia

    INDEX
    Explanations

    aria-label, alt, label, or expanded attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UIntValue
    0.39
    ześnie
    0.39
    advised
    0.38
    recommended
    0.37
     फंक्शन
    0.37
    推薦
    0.37
    behaved
    0.37
     negotiated
    0.36
    straight
    0.36
    推荐
    0.36
    POSITIVE LOGITS
    Close
    0.44
     Close
    0.44
     close
    0.43
     tiền
    0.39
    close
    0.38
    CLOSE
    0.37
     cơ
    0.37
    閉じ
    0.37
     enzyme
    0.36
     ดัง
    0.36
    Act Density 0.000%

    No Known Activations