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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GroupLayout
    -0.07
    Dlg
    -0.07
    amac
    -0.06
    其实
    -0.06
     Unicorn
    -0.06
    이라고
    -0.06
     cũng
    -0.06
    _topics
    -0.06
    buster
    -0.06
     почти
    -0.06
    POSITIVE LOGITS
    dap
    0.07
    -Speed
    0.07
    (fields
    0.06
    يج
    0.06
     [%
    0.06
     результате
    0.06
    рап
    0.06
    [date
    0.06
    ala
    0.06
    ictures
    0.06
    Act Density 0.000%

    No Known Activations