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

    Neuronpedia

    INDEX
    Explanations

    referral, training, datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кто
    0.43
     afect
    0.43
    رفت
    0.43
     applied
    0.40
    ষ
    0.39
     embarking
    0.39
     affect
    0.39
     thriving
    0.39
     heating
    0.38
    Tennis
    0.38
    POSITIVE LOGITS
     =~
    0.48
    િવસ
    0.47
    推奨
    0.45
    ᵁ
    0.45
    션을
    0.44
    の色
    0.44
     урна
    0.44
    bew
    0.43
    ections
    0.43
    ಿರಿ
    0.43
    Act Density 0.000%

    No Known Activations