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

    Neuronpedia

    INDEX
    Explanations

    core, main, specific, different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೇಳ
    0.48
     Langevin
    0.48
    চন্দ্র
    0.46
    㗽
    0.46
     Laksh
    0.45
     poplar
    0.45
     表示
    0.45
     AsyncStorage
    0.44
     elects
    0.43
    INR
    0.42
    POSITIVE LOGITS
    、
    0.52
    де
    0.48
    比
    0.46
     bukanlah
    0.46
    уда
    0.45
    П
    0.45
    за
    0.44
    ،
    0.44
     intermedi
    0.43
    зами
    0.42
    Act Density 0.001%

    No Known Activations