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

    Neuronpedia

    INDEX
    Explanations

    selling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]='\
    -0.07
     govern
    -0.07
    від
    -0.06
    杯
    -0.06
     getopt
    -0.06
    409
    -0.06
    随
    -0.06
     På
    -0.06
    880
    -0.06
     lead
    -0.06
    POSITIVE LOGITS
    (lista
    0.07
    íf
    0.07
    "><?
    0.07
     Quality
    0.06
    oteca
    0.06
    審
    0.06
     širo
    0.06
    ्ठ
    0.06
    出售
    0.06
    amı
    0.06
    Act Density 0.016%

    No Known Activations