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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dued
    -0.07
    compressed
    -0.07
     clums
    -0.07
    г
    -0.07
    TemplateName
    -0.06
    zyć
    -0.06
     preempt
    -0.06
     preço
    -0.06
     Fernando
    -0.06
    serialized
    -0.06
    POSITIVE LOGITS
     millet
    0.07
    (IT
    0.07
     七
    0.06
     @{
    0.06
    ).(
    0.06
    除了
    0.06
    *:
    0.06
    evším
    0.06
    &p
    0.06
    .baomidou
    0.06
    Act Density 0.008%

    No Known Activations