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

    Neuronpedia

    INDEX
    Explanations

    Parsing word/math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _INS
    -0.08
    tent
    -0.08
     silic
    -0.08
     pendientes
    -0.08
     demonstrating
    -0.08
    rek
    -0.07
     dormant
    -0.07
    /global
    -0.07
     मुक्त
    -0.07
    Tent
    -0.07
    POSITIVE LOGITS
     rhyme
    0.10
    谜
    0.09
     wording
    0.09
     المذك
    0.09
     contradictory
    0.09
     portrayed
    0.08
     представлен
    0.08
     anecd
    0.08
     店
    0.08
     introduced
    0.08
    Act Density 0.107%

    No Known Activations