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

    Neuronpedia

    INDEX
    Explanations

    code headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bits
    -0.07
     attaches
    -0.07
     Today
    -0.06
    _az
    -0.06
    。あ
    -0.06
    Flow
    -0.06
     Melissa
    -0.06
    078
    -0.06
    filer
    -0.06
    _ENTITY
    -0.06
    POSITIVE LOGITS
    (resultSet
    0.07
     налог
    0.06
    scriptions
    0.06
    *>(
    0.06
     *>(
    0.06
    .den
    0.06
    (Me
    0.06
    加工
    0.06
    (by
    0.06
    .weapon
    0.06
    Act Density 0.001%

    No Known Activations