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

    Neuronpedia

    INDEX
    Explanations

    availability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nond
    -0.08
     WORD
    -0.08
     acad
    -0.07
     IDC
    -0.07
     possess
    -0.07
    尾
    -0.07
    يدر
    -0.07
     विद्यालय
    -0.07
     LIM
    -0.07
     σκ
    -0.07
    POSITIVE LOGITS
    HAM
    0.08
     العالية
    0.08
     Reliability
    0.08
     uptime
    0.08
     ema
    0.08
     fluctuations
    0.07
    (net
    0.07
     interruptions
    0.07
    ocol
    0.07
     mio
    0.07
    Act Density 0.007%

    No Known Activations