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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hun
    -0.07
     مکانی
    -0.07
     mlad
    -0.07
     dealership
    -0.07
    撤
    -0.06
     عندما
    -0.06
     lyr
    -0.06
     landsc
    -0.06
     Logging
    -0.06
    outdir
    -0.06
    POSITIVE LOGITS
     Shot
    0.06
    озя
    0.06
    ックス
    0.06
    کم
    0.06
    ุล
    0.06
    �
    0.06
    ْن
    0.06
     motivating
    0.06
     нему
    0.06
     chests
    0.06
    Act Density 0.030%

    No Known Activations