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

    Neuronpedia

    INDEX
    Explanations

    Holmes or Hol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flourishing
    -0.07
     decrease
    -0.07
    анта
    -0.07
    mensaje
    -0.06
    +
    -0.06
    /items
    -0.06
     YEARS
    -0.06
    .org
    -0.06
    -V
    -0.06
     baseline
    -0.06
    POSITIVE LOGITS
    DMI
    0.07
    _phr
    0.06
    PEND
    0.06
    _OBJC
    0.06
     设
    0.06
    tec
    0.06
    خم
    0.06
    aju
    0.06
    美元
    0.06
    иля
    0.06
    Act Density 0.030%

    No Known Activations