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

    Neuronpedia

    INDEX
    Explanations

    smart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fd
    -0.08
    оск
    -0.07
     Shutterstock
    -0.06
    ivol
    -0.06
    ิกายน
    -0.06
    üml
    -0.06
    ораль
    -0.06
    urrection
    -0.06
     pob
    -0.06
    rát
    -0.06
    POSITIVE LOGITS
    0.07
     Period
    0.06
     blazing
    0.06
    (INPUT
    0.06
    zenia
    0.06
     clases
    0.06
    _rng
    0.06
     Navy
    0.06
    某
    0.06
     prematurely
    0.06
    Act Density 0.005%

    No Known Activations