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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     governments
    -0.07
    lue
    -0.06
    -Bar
    -0.06
     body
    -0.06
    Phi
    -0.06
    _CN
    -0.06
    ゥ
    -0.06
     }.
    -0.06
    -b
    -0.06
    sd
    -0.06
    POSITIVE LOGITS
    .generator
    0.08
    _pipe
    0.07
     پژ
    0.07
    .CON
    0.06
     Charlottesville
    0.06
    (off
    0.06
    (mut
    0.06
    ovaných
    0.06
     घटन
    0.06
     سیاست
    0.06
    Act Density 0.008%

    No Known Activations