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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serotonin
    -0.07
    ्सर
    -0.07
    _Column
    -0.06
    neutral
    -0.06
    Semantic
    -0.06
    riad
    -0.06
     glVertex
    -0.06
     DG
    -0.06
    将
    -0.06
     beneath
    -0.06
    POSITIVE LOGITS
    >").
    0.07
     README
    0.07
     ô
    0.06
     деле
    0.06
    玉
    0.06
    �
    0.06
     Lưu
    0.06
    _NAME
    0.06
    โลย
    0.06
     taşım
    0.06
    Act Density 0.020%

    No Known Activations