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

    Neuronpedia

    INDEX
    Explanations

    Code/math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chairs
    -0.07
     tracked
    -0.07
     hygiene
    -0.07
     commenting
    -0.07
     McCorm
    -0.06
    city
    -0.06
     feels
    -0.06
     owners
    -0.06
    sem
    -0.06
     Snow
    -0.06
    POSITIVE LOGITS
    RESET
    0.07
    بن
    0.06
     네이트온
    0.06
     فوق
    0.06
    .scalajs
    0.06
    ﾄ
    0.06
    -character
    0.06
     artikel
    0.06
    :CGPoint
    0.06
    ط
    0.06
    Act Density 0.002%

    No Known Activations