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

    Neuronpedia

    INDEX
    Explanations

    AFL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    di
    -0.06
    _classifier
    -0.06
    /settings
    -0.06
     Québec
    -0.06
    avascript
    -0.06
    DI
    -0.06
    ++);↵
    -0.06
    Kenn
    -0.06
     LB
    -0.06
    ::~
    -0.06
    POSITIVE LOGITS
    (Bit
    0.07
     corporations
    0.06
     sophistication
    0.06
    .Ş
    0.06
    .makedirs
    0.06
    <f
    0.06
    تيار
    0.06
    .XR
    0.06
    _RED
    0.06
     delight
    0.06
    Act Density 0.023%

    No Known Activations