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

    Neuronpedia

    INDEX
    Explanations

    questions, records, millions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Experts
    0.46
     News
    0.45
     puppies
    0.43
     effic
    0.42
     তখনও
    0.42
    ᐅ
    0.42
     experts
    0.42
     Nhân
    0.42
     dollars
    0.42
     Millions
    0.42
    POSITIVE LOGITS
    have
    0.47
     have
    0.46
    angwa
    0.42
    ματο
    0.39
    вался
    0.38
    валася
    0.37
    विष्ट
    0.37
    施設の
    0.37
    irono
    0.37
     beset
    0.37
    Act Density 0.000%

    No Known Activations