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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bias
    -0.07
    .bt
    -0.07
     Mỹ
    -0.07
    _sender
    -0.07
    closure
    -0.07
    จำนวนมาก
    -0.07
    -green
    -0.07
     Pré
    -0.07
    grey
    -0.07
    bmp
    -0.07
    POSITIVE LOGITS
    ываем
    0.07
    收购
    0.07
     "---
    0.07
    Daemon
    0.07
    Natural
    0.07
    七大
    0.07
    牽
    0.06
    .decorators
    0.06
    lys
    0.06
    യ
    0.06
    Act Density 0.002%

    No Known Activations