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

    Neuronpedia

    INDEX
    Explanations

    types of styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transformative
    0.43
     forfeiture
    0.42
     говори
    0.41
    انس
    0.41
    ницей
    0.40
     ለአ
    0.40
    低的
    0.40
    vective
    0.40
     culturally
    0.38
    IDENCE
    0.38
    POSITIVE LOGITS
     Same
    0.41
     검
    0.41
    errorMessage
    0.40
    検
    0.39
    QA
    0.38
    mbox
    0.38
    Generated
    0.37
     Messe
    0.37
     QMessageBox
    0.37
    qa
    0.37
    Act Density 0.005%

    No Known Activations