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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MONTH
    -0.07
    .Visibility
    -0.07
    EXPECT
    -0.06
    ída
    -0.06
    غيرة
    -0.06
     Vij
    -0.06
     taşım
    -0.06
    227
    -0.06
    _:
    -0.06
    σή
    -0.06
    POSITIVE LOGITS
     appears
    0.07
    .requires
    0.07
    握
    0.07
     appear
    0.07
    -West
    0.07
     came
    0.07
     عمر
    0.06
     appeared
    0.06
    造成
    0.06
     reachable
    0.06
    Act Density 0.008%

    No Known Activations