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

    Neuronpedia

    INDEX
    Explanations

    code and text mix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     γ
    -0.07
     adap
    -0.06
     canv
    -0.06
     circulated
    -0.06
     заяв
    -0.06
    ainless
    -0.06
    ourses
    -0.06
     Drum
    -0.06
    -F
    -0.06
    aaaaaaaa
    -0.06
    POSITIVE LOGITS
     diş
    0.07
    (dummy
    0.07
     tendon
    0.07
    _mult
    0.07
     buurt
    0.06
     maple
    0.06
     bola
    0.06
    <pair
    0.06
    ализа
    0.06
     positional
    0.06
    Act Density 0.000%

    No Known Activations