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

    Neuronpedia

    INDEX
    Explanations

    IE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .course
    -0.07
     RFID
    -0.06
    HAS
    -0.06
    Christopher
    -0.06
     XS
    -0.06
    .gameserver
    -0.06
     likely
    -0.06
     FML
    -0.06
     Jarvis
    -0.06
     HQ
    -0.06
    POSITIVE LOGITS
     imperfect
    0.07
    �
    0.07
    数学
    0.06
    amina
    0.06
    тр
    0.06
     thu
    0.06
     actresses
    0.06
     relics
    0.06
     качества
    0.06
     pret
    0.06
    Act Density 0.001%

    No Known Activations