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

    Neuronpedia

    INDEX
    Explanations

    substantial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     power
    -0.07
    ddit
    -0.07
    o
    -0.07
    iras
    -0.07
    _battery
    -0.07
    σμός
    -0.07
     days
    -0.06
    /debug
    -0.06
     �
    -0.06
    (interface
    -0.06
    POSITIVE LOGITS
     Kro
    0.06
     consistently
    0.06
    etSocketAddress
    0.06
    ombine
    0.06
     значительно
    0.06
     несколько
    0.06
     lasts
    0.06
     useDispatch
    0.06
     multiplied
    0.06
     laten
    0.06
    Act Density 0.001%

    No Known Activations