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

    Neuronpedia

    INDEX
    Explanations

    perturbation theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ned
    -0.07
    墐
    -0.07
     마지
    -0.07
    แห
    -0.06
    升温
    -0.06
    馆
    -0.06
    <Cell
    -0.06
    �
    -0.06
    ijd
    -0.06
    <lemma
    -0.06
    POSITIVE LOGITS
     Barg
    0.08
     Derek
    0.07
     disturbance
    0.07
    깓
    0.07
    𝑤
    0.07
     décision
    0.07
     (%
    0.07
     gord
    0.06
    烏
    0.06
     SP
    0.06
    Act Density 0.002%

    No Known Activations