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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wann
    -0.08
    -neg
    -0.08
     قر
    -0.07
     lately
    -0.07
    .");↵↵
    -0.07
    زمة
    -0.07
    ");↵↵
    -0.07
    obby
    -0.07
     inom
    -0.07
    äck
    -0.07
    POSITIVE LOGITS
     Optimal
    0.09
     closest
    0.09
     bouch
    0.08
     buz
    0.08
     отметить
    0.07
    ，此
    0.07
     Ukraina
    0.07
     spéciale
    0.07
    /styles
    0.07
     servo
    0.07
    Act Density 0.099%

    No Known Activations