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

    Neuronpedia

    INDEX
    Explanations

    transistors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    县
    -0.07
     unserialize
    -0.07
    اكم
    -0.07
    Ethernet
    -0.07
     subnet
    -0.07
     decrease
    -0.06
     root
    -0.06
    Contours
    -0.06
    fty
    -0.06
    最初
    -0.06
    POSITIVE LOGITS
     ED
    0.07
    úng
    0.06
    BUY
    0.06
     Simpl
    0.06
    мож
    0.06
    _Selected
    0.06
    ’B
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
     Reality
    0.06
     Willie
    0.06
    Act Density 0.017%

    No Known Activations