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

    Neuronpedia

    INDEX
    Explanations

    Code and miscellaneous text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     прок
    -0.07
     sû
    -0.06
     chilly
    -0.06
     tarea
    -0.06
     γρα
    -0.06
     fos
    -0.06
     habit
    -0.06
     có
    -0.06
     존재
    -0.06
     GOP
    -0.06
    POSITIVE LOGITS
     Rivera
    0.07
    Erreur
    0.07
     Gene
    0.07
    ерату
    0.06
     Tristan
    0.06
    ])))
    0.06
    elix
    0.06
    ?).
    0.06
    )):
    0.06
     porcelain
    0.06
    Act Density 0.000%

    No Known Activations