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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     races
    -0.07
     untuk
    -0.07
     urgent
    -0.07
     ucz
    -0.07
    race
    -0.06
     funct
    -0.06
     cellForRowAt
    -0.06
    h
    -0.06
     weighting
    -0.06
     elections
    -0.06
    POSITIVE LOGITS
     nebyla
    0.07
     complexity
    0.07
    (dst
    0.06
    εργ
    0.06
    PLICATION
    0.06
    líž
    0.06
     pohled
    0.06
    Nib
    0.06
     He
    0.06
     مشخص
    0.06
    Act Density 0.002%

    No Known Activations