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

    Neuronpedia

    INDEX
    Explanations

    should use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ia
    0.51
     self
    0.51
     Zimmerman
    0.47
    ]][
    0.46
     (:
    0.45
     ocor
    0.44
    iano
    0.44
     Confederacy
    0.44
     proliferation
    0.44
     shuffled
    0.43
    POSITIVE LOGITS
    ﺮ
    0.50
    را
    0.49
    স
    0.49
    زى
    0.49
    الغ
    0.48
     أك
    0.47
    رك
    0.47
    ات
    0.47
    الص
    0.47
    است
    0.46
    Act Density 0.000%

    No Known Activations