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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [port
    -0.07
    有关
    -0.07
     нам
    -0.07
    (station
    -0.07
     být
    -0.06
     зуп
    -0.06
     exploit
    -0.06
     harms
    -0.06
    salary
    -0.06
     dire
    -0.06
    POSITIVE LOGITS
     smile
    0.06
     rost
    0.06
    ebb
    0.06
    rian
    0.06
     عاما
    0.06
     Formatting
    0.06
     Noah
    0.06
     demeanor
    0.06
     simplicity
    0.06
     Adam
    0.06
    Act Density 0.012%

    No Known Activations