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

    Neuronpedia

    INDEX
    Explanations

    em dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _five
    -0.07
     backwards
    -0.06
     schemes
    -0.06
     Tree
    -0.06
    egin
    -0.06
    86
    -0.06
    ever
    -0.06
    .dot
    -0.06
    .',
    -0.06
     scooter
    -0.06
    POSITIVE LOGITS
     Σε
    0.07
     напря
    0.06
    transactions
    0.06
     opatření
    0.06
    辰
    0.06
    ١
    0.06
    logue
    0.06
     Spo
    0.06
     Jazeera
    0.06
    BODY
    0.06
    Act Density 0.014%

    No Known Activations