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

    Neuronpedia

    INDEX
    Explanations

    end of a time period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mess
    -0.08
     Finder
    -0.08
     само
    -0.08
     множество
    -0.08
     autod
    -0.08
    _aut
    -0.08
     दर्ज
    -0.07
     kant
    -0.07
     Aut
    -0.07
    Aut
    -0.07
    POSITIVE LOGITS
     reached
    0.10
    (before
    0.10
     Rodríguez
    0.09
    -stage
    0.09
     단계
    0.09
     этап
    0.09
    阶段
    0.09
     cheg
    0.09
     غسل
    0.09
    (after
    0.09
    Act Density 0.019%

    No Known Activations