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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unleashed
    -0.07
    Пр
    -0.06
    坦
    -0.06
    -type
    -0.06
    :absolute
    -0.06
     питань
    -0.06
     étaient
    -0.06
     Tender
    -0.06
    .readValue
    -0.06
    週
    -0.06
    POSITIVE LOGITS
    .array
    0.08
     Gret
    0.07
     phys
    0.06
    arDown
    0.06
     Ros
    0.06
    enan
    0.06
     meant
    0.06
    ̈
    0.06
     Packers
    0.06
    auto
    0.06
    Act Density 0.009%

    No Known Activations