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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ４
    -0.09
    now
    -0.07
     Ale
    -0.07
     зал
    -0.07
    ques
    -0.07
    ३
    -0.07
     chce
    -0.07
    Impossible
    -0.07
     ISIL
    -0.07
     Guard
    -0.06
    POSITIVE LOGITS
    urgeon
    0.06
    />
↵
    0.06
    +m
    0.06
    QUENCE
    0.06
     MAC
    0.06
    .netflix
    0.06
     compassionate
    0.06
     připoj
    0.06
     {{--<
    0.06
    rious
    0.06
    Act Density 0.099%

    No Known Activations