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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ಬೇಕು
    -0.07
    ಬೇಕ
    -0.07
     dissatisfied
    -0.07
    岸
    -0.07
     technician
    -0.07
    拟
    -0.07
    ，非常
    -0.07
     gemak
    -0.07
     уют
    -0.07
    POSITIVE LOGITS
     gcd
    0.12
     modulo
    0.11
    Modulo
    0.10
     divisible
    0.10
     mã
    0.09
     numerator
    0.09
     vulnerability
    0.09
    Bez
    0.08
     multiples
    0.08
     congr
    0.08
    Act Density 0.060%

    No Known Activations