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

    Neuronpedia

    INDEX
    Explanations

    knee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ions
    -0.07
     giai
    -0.06
    ilde
    -0.06
    cost
    -0.06
    áng
    -0.06
     COM
    -0.06
    MD
    -0.06
     AI
    -0.06
    feedback
    -0.06
     portions
    -0.06
    POSITIVE LOGITS
     knee
    0.14
     Knee
    0.12
     knees
    0.09
    焦
    0.07
    \brief
    0.07
     Trades
    0.07
     Cover
    0.06
     Pumpkin
    0.06
    _DAYS
    0.06
     prac
    0.06
    Act Density 0.003%

    No Known Activations