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

    Neuronpedia

    INDEX
    Explanations

    brackets and get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .decode
    -0.08
    (sensor
    -0.07
     jug
    -0.07
    ");//
    -0.07
    ální
    -0.07
    decode
    -0.07
     %,
    -0.07
    );}
    -0.07
    Android
    -0.06
     ////
    -0.06
    POSITIVE LOGITS
     prostitu
    0.06
     mw
    0.06
     пла
    0.06
     sanitation
    0.06
     initWithFrame
    0.06
    _PROF
    0.06
     cheesy
    0.06
    _mouse
    0.05
    nement
    0.05
     gehen
    0.05
    Act Density 0.343%

    No Known Activations