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

    Neuronpedia

    INDEX
    Explanations

    argparse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     공격
    -0.07
     x
    -0.07
     comm
    -0.07
     gent
    -0.07
    ometry
    -0.07
     виріш
    -0.07
    ];↵↵
    -0.06
    .addr
    -0.06
    -success
    -0.06
    .ByteArray
    -0.06
    POSITIVE LOGITS
    ��드
    0.07
     полностью
    0.06
    Reminder
    0.06
    ellidos
    0.06
    訳
    0.06
     Lahore
    0.06
    ابعة
    0.06
     nuestros
    0.06
    ائه
    0.06
    這
    0.06
    Act Density 0.003%

    No Known Activations