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

    Neuronpedia

    INDEX
    Explanations

    rust safety and ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arist
    0.46
    เพราะ
    0.43
     leaking
    0.42
     библиотеки
    0.42
     shuffling
    0.42
    酴
    0.40
    ະພັນ
    0.40
    ግሎ
    0.40
    汚
    0.40
    Arist
    0.39
    POSITIVE LOGITS
    ipynb
    0.41
     Cup
    0.38
     knuckle
    0.36
     CF
    0.35
     Tf
    0.35
     EMEA
    0.35
    轧
    0.35
     UFC
    0.34
     Cf
    0.34
    ติ
    0.34
    Act Density 0.007%

    No Known Activations