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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bind
    -0.09
     숨
    -0.09
     منص
    -0.09
    (Collections
    -0.09
    Guests
    -0.09
    Falsy
    -0.09
    Mensaje
    -0.08
    め
    -0.08
     fundraising
    -0.08
    _MESSAGE
    -0.08
    POSITIVE LOGITS
    氏
    0.11
     theorem
    0.11
     सिद्ध
    0.11
     Johnson
    0.10
     Clarke
    0.10
     Pratt
    0.10
     Law
    0.10
     equations
    0.09
    197
    0.09
     patented
    0.09
    Act Density 0.058%

    No Known Activations