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

    Neuronpedia

    INDEX
    Explanations

    if something is good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     start
    -0.07
     наук
    -0.06
     firmly
    -0.06
     Navbar
    -0.06
    aks
    -0.06
     almost
    -0.06
    Str
    -0.06
    _query
    -0.06
     crude
    -0.06
    enarios
    -0.06
    POSITIVE LOGITS
    _arch
    0.07
    “Well
    0.06
     Baron
    0.06
    ribly
    0.06
    BeginInit
    0.06
     अश
    0.06
    rounded
    0.06
    CHANNEL
    0.06
    .Chain
    0.06
    ibase
    0.06
    Act Density 0.004%

    No Known Activations