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

    Neuronpedia

    INDEX
    Explanations

    mathematical problem solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gelungen
    -0.08
     Soviet
    -0.08
     accessories
    -0.07
    Bow
    -0.07
    _arrow
    -0.07
     эта
    -0.07
     Moscow
    -0.07
     нравится
    -0.07
     презента
    -0.07
     trad
    -0.07
    POSITIVE LOGITS
    ebut
    0.10
     Jusqu
    0.09
     razo
    0.09
     foreseeable
    0.09
     Reason
    0.09
     upto
    0.09
     brute
    0.09
     exib
    0.09
     reasonable
    0.09
    Reason
    0.09
    Act Density 0.047%

    No Known Activations