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

    Neuronpedia

    INDEX
    Explanations

    purpose of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Europ
    0.38
    dates
    0.38
    Program
    0.38
    Ped
    0.37
    program
    0.36
     experts
    0.36
    નિક
    0.36
    Recall
    0.35
     Experts
    0.35
    洼
    0.35
    POSITIVE LOGITS
    revalidator
    0.49
    >().
    0.41
    </thead>
    0.41
    emptyDict
    0.41
     المثلثيه
    0.41
    multiSelectList
    0.40
     चैप्टर्स
    0.40
    อื่นๆ
    0.40
     Smoky
    0.40
    ทะ
    0.40
    Act Density 0.000%

    No Known Activations