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

    Neuronpedia

    INDEX
    Explanations

    route title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تي
    0.44
     روشن
    0.43
    pyridazine
    0.41
     Kamer
    0.39
    jetas
    0.39
    ittees
    0.38
    GOND
    0.38
    cx
    0.37
    the
    0.37
     sabato
    0.37
    POSITIVE LOGITS
     parody
    0.45
    ್ಯಾ
    0.45
    ）」
    0.41
     Stroke
    0.41
    ெடு
    0.39
     വ്യാപ
    0.37
    AssetDiscovery
    0.37
    とり
    0.37
    CCESS
    0.37
     выборе
    0.37
    Act Density 0.000%

    No Known Activations