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

    Neuronpedia

    INDEX
    Explanations

    predict how humans rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HALF
    0.45
    َع
    0.43
    canceled
    0.43
    ومي
    0.42
    реди
    0.41
    ̝
    0.41
    half
    0.40
    進
    0.40
     upset
    0.40
    pyridin
    0.40
    POSITIVE LOGITS
     PDA
    0.47
    ərd
    0.46
     Bibliography
    0.44
     Stove
    0.44
    ský
    0.43
     سایر
    0.43
     Materials
    0.43
    ኛውም
    0.43
     CTA
    0.43
     Gebä
    0.43
    Act Density 0.003%

    No Known Activations