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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ναν
    -0.08
     refers
    -0.08
     POL
    -0.08
     составляет
    -0.08
     sebesar
    -0.08
    _net
    -0.08
     reconnaissance
    -0.07
     refiere
    -0.07
    ใบ
    -0.07
     धम
    -0.07
    POSITIVE LOGITS
     ઇન્ડ
    0.08
     Example
    0.08
    alaya
    0.07
     imposible
    0.07
     illustrative
    0.07
    ondra
    0.07
     اف
    0.07
     eksempel
    0.07
    ENDS
    0.07
     उदाहरण
    0.07
    Act Density 0.041%

    No Known Activations