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

    Neuronpedia

    INDEX
    Explanations

    except

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MATRIX
    -0.07
    อให
    -0.07
    UIImage
    -0.06
     wei
    -0.06
    Rand
    -0.06
    .keras
    -0.06
     Anal
    -0.06
    热
    -0.06
    中心
    -0.06
     vrij
    -0.06
    POSITIVE LOGITS
    इन
    0.07
    utely
    0.07
    Engine
    0.07
     ignore
    0.06
     Sunshine
    0.06
    ea
    0.06
     Geld
    0.06
     Велик
    0.06
    uttle
    0.06
     सरक
    0.06
    Act Density 0.001%

    No Known Activations