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

    Neuronpedia

    INDEX
    Explanations

    import statements or package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒈬
    0.26
     vattum
    0.25
     ذکر
    0.25
     histological
    0.24
     पुस्त
    0.24
    忏
    0.24
     توضیح
    0.23
     hémorro
    0.23
    হাম্ম
    0.23
    咊
    0.23
    POSITIVE LOGITS
    i
    0.31
    to
    0.27
    ="
    0.27
    “
    0.26
    1
    0.25
    )
    0.24
     to
    0.24
    S
    0.24
    -
    0.24
    ↵
    0.24
    Act Density 0.001%

    No Known Activations