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

    Neuronpedia

    INDEX
    Explanations

    Scientific measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cán
    -0.07
    baum
    -0.07
    됨
    -0.07
    ratulations
    -0.07
    bcm
    -0.07
     člověka
    -0.06
    شنبه
    -0.06
    ��
    -0.06
     сказать
    -0.06
    ();

↵
    -0.06
    POSITIVE LOGITS
    ucing
    0.07
     Allied
    0.06
     кас
    0.06
    控
    0.06
    -engine
    0.06
     unaware
    0.06
     royalties
    0.06
     Rack
    0.06
     patents
    0.06
    TC
    0.06
    Act Density 0.008%

    No Known Activations