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

    Neuronpedia

    INDEX
    Explanations

    Kal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     هنا
    -0.08
    お勧め
    -0.07
    胧
    -0.07
    ítulo
    -0.07
    こんな
    -0.07
    .Trim
    -0.07
    /swagger
    -0.07
    dns
    -0.07
     Cheers
    -0.07
    深处
    -0.07
    POSITIVE LOGITS
    '):
↵
    0.08
    '):↵
    0.08
    _calendar
    0.07
    _individual
    0.07
    liament
    0.07
    _interrupt
    0.07
    "):↵
    0.07
     Serious
    0.07
     kä
    0.07
    κ
    0.06
    Act Density 0.006%

    No Known Activations