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

    Neuronpedia

    INDEX
    Explanations

    alert, urgency, or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    綀
    0.41
     Hartree
    0.41
    কেশন
    0.41
    iume
    0.40
    ेंटीना
    0.40
    iliate
    0.39
    ͤ
    0.39
    scheduler
    0.39
    enuine
    0.39
     النسبيه
    0.39
    POSITIVE LOGITS
     menos
    0.44
     bow
    0.43
    Gri
    0.38
    ForRow
    0.37
    Kep
    0.37
     closer
    0.37
    For
    0.36
     alert
    0.36
     од
    0.36
    另一方面
    0.36
    Act Density 0.000%

    No Known Activations