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

    Neuronpedia

    INDEX
    Explanations

    islands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Devils
    -0.08
     Bh
    -0.07
    _construct
    -0.07
     JavaScript
    -0.07
    av
    -0.07
    (regex
    -0.06
     Dh
    -0.06
     bezpečnost
    -0.06
    >B
    -0.06
    들도
    -0.06
    POSITIVE LOGITS
     sadd
    0.06
     ninete
    0.06
     erfol
    0.06
    �
    0.06
     ά
    0.06
    <i
    0.06
     Alternate
    0.06
     Speed
    0.06
     先
    0.06
     звер
    0.06
    Act Density 0.057%

    No Known Activations