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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _GRANTED
    -0.07
     IndexError
    -0.07
    .readAs
    -0.06
    .FileOutputStream
    -0.06
     Çev
    -0.06
     iface
    -0.06
    .sw
    -0.06
     Tribute
    -0.06
     congestion
    -0.06
    Recognition
    -0.06
    POSITIVE LOGITS
    abic
    0.07
    جز
    0.07
    OPT
    0.06
    ρά
    0.06
    udios
    0.06
    验
    0.06
     přen
    0.06
    kul
    0.06
     involves
    0.06
     includes
    0.06
    Act Density 0.043%

    No Known Activations