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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    can
    -0.07
    sw
    -0.06
    _sorted
    -0.06
    Learn
    -0.06
     rainy
    -0.06
    DataGridView
    -0.06
    Authority
    -0.06
    @↵
    -0.06
     lan
    -0.06
    _even
    -0.06
    POSITIVE LOGITS
     enticing
    0.07
    レ
    0.07
    .misc
    0.06
    Insensitive
    0.06
    _AREA
    0.06
    program
    0.06
    اجر
    0.06
    ">${
    0.06
    _Profile
    0.06
    蓝
    0.06
    Act Density 0.000%

    No Known Activations