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

    Neuronpedia

    INDEX
    Explanations

    icc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hound
    -0.07
    렁
    -0.07
    떈
    -0.07
    焆
    -0.07
     Phill
    -0.06
    ['<{
    -0.06
    与众
    -0.06
    ⮟
    -0.06
     prime
    -0.06
    跳出
    -0.06
    POSITIVE LOGITS
    0.07
    ateurs
    0.07
    0.07
     Hab
    0.07
    _proj
    0.07
     viscosity
    0.07
    ickle
    0.07
     Pressure
    0.07
     userdata
    0.07
    (iter
    0.07
    Act Density 0.001%

    No Known Activations