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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .partition
    -0.07
    (record
    -0.07
    storybook
    -0.07
    .custom
    -0.07
    dbus
    -0.07
    partition
    -0.07
    (int
    -0.06
    \Contracts
    -0.06
    beta
    -0.06
    (api
    -0.06
    POSITIVE LOGITS
    ประม
    0.07
     unused
    0.06
    rně
    0.06
    ensem
    0.06
    iệu
    0.06
    icals
    0.06
    departments
    0.06
     cleanly
    0.06
    ().'/
    0.06
    aunch
    0.06
    Act Density 0.021%

    No Known Activations