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

    Neuronpedia

    INDEX
    Explanations

    except Exception, can comfortably

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     useless
    1.43
     restrooms
    1.25
     fatally
    1.24
     phenolic
    1.24
    нії
    1.22
     fastapi
    1.22
     USART
    1.22
    〝
    1.22
    း
    1.21
     teachers
    1.21
    POSITIVE LOGITS
    타
    1.27
     Quels
    1.06
    ɪ
    0.97
     quelles
    0.97
    irmek
    0.97
    má
    0.94
    곡
    0.94
    굴
    0.93
    mey
    0.92
    pandemic
    0.92
    Act Density 0.000%

    No Known Activations