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

    Neuronpedia

    INDEX
    Explanations

    Statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еня
    -0.06
    _definitions
    -0.06
    _CAPTURE
    -0.06
     मन
    -0.06
    ملة
    -0.06
    .LinkedList
    -0.06
     Demon
    -0.06
     prank
    -0.06
    elastic
    -0.06
     Peel
    -0.05
    POSITIVE LOGITS
     historically
    0.07
     �
    0.07
    .")
↵
    0.07
    许多
    0.06
    -binding
    0.06
    umd
    0.06
     warranty
    0.06
    .
    0.06
    सत
    0.06
     kiện
    0.06
    Act Density 0.108%

    No Known Activations