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

    Neuronpedia

    INDEX
    Explanations

    code/math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     태
    -0.07
    Interface
    -0.07
    &m
    -0.06
    "F
    -0.06
     analogue
    -0.06
     채
    -0.06
     Phần
    -0.06
    .wr
    -0.06
    choice
    -0.06
    ımlı
    -0.05
    POSITIVE LOGITS
    arium
    0.07
     гум
    0.06
     пунк
    0.06
    .await
    0.06
    tributes
    0.06
    ункт
    0.06
     перепис
    0.06
     آباد
    0.06
    reh
    0.06
    forces
    0.06
    Act Density 0.039%

    No Known Activations