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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     özel
    -0.07
    �
    -0.07
     Colum
    -0.07
    泓
    -0.07
     direkt
    -0.07
     krist
    -0.07
     Rex
    -0.07
    所有人都
    -0.07
    就
    -0.06
     sektör
    -0.06
    POSITIVE LOGITS
    _NORMAL
    0.07
    spent
    0.07
    .getContext
    0.07
     SUMMARY
    0.07
     M
    0.07
    inan
    0.07
    _extract
    0.07
     stutter
    0.07
    排出
    0.07
    能耗
    0.07
    Act Density 0.010%

    No Known Activations