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

    Neuronpedia

    INDEX
    Explanations

    a.

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     came
    0.25
    ↵
    0.25
     your
    0.23
     the
    0.23
    брав
    0.23
    왔
    0.23
     buggy
    0.23
     took
    0.22
     gets
    0.22
    ل
    0.22
    POSITIVE LOGITS
    ulence
    0.28
    versions
    0.27
     sensibilities
    0.27
     inferences
    0.26
    ्ञ
    0.26
    ুগত্য
    0.26
     beliefs
    0.25
     predisposition
    0.25
    の原因
    0.25
     borrowings
    0.25
    Act Density 0.073%

    No Known Activations