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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kách
    -0.07
    :.:.:.:.:
    -0.06
    采用
    -0.06
    分别
    -0.06
    035
    -0.06
     από
    -0.06
    عنی
    -0.06
     Presidential
    -0.06
     debugging
    -0.06
    ěti
    -0.06
    POSITIVE LOGITS
    -long
    0.07
    Instr
    0.06
     judgments
    0.06
    αιο
    0.06
    ед
    0.06
    buffers
    0.06
     활동
    0.05
    „J
    0.05
    Members
    0.05
     Compilation
    0.05
    Act Density 0.046%

    No Known Activations