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

    Neuronpedia

    INDEX
    Explanations

    robots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _counter
    -0.06
     úprav
    -0.06
    огра
    -0.06
     často
    -0.06
    มาร
    -0.06
     interacting
    -0.06
     Fleming
    -0.06
     composers
    -0.06
    ْه
    -0.06
     Week
    -0.06
    POSITIVE LOGITS
    sbin
    0.06
     experimenting
    0.06
    担当
    0.06
    vál
    0.06
     resil
    0.06
     PyErr
    0.06
    (system
    0.05
    ="{{$
    0.05
    hero
    0.05
     rallies
    0.05
    Act Density 0.053%

    No Known Activations