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

    Neuronpedia

    INDEX
    Explanations

    Service Desk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SAT
    0.36
    一つの
    0.36
     Poppy
    0.35
    タイミング
    0.35
     Yuan
    0.35
     इंटरेस्ट
    0.35
    alal
    0.35
     ühe
    0.35
     [--
    0.35
     могу
    0.35
    POSITIVE LOGITS
     folk
    0.45
    Гц
    0.45
     pedagogical
    0.43
     nipple
    0.41
     fb
    0.40
    訾
    0.40
     //</
    0.38
     bolt
    0.37
     FileWriter
    0.36
    ivil
    0.36
    Act Density 0.000%

    No Known Activations