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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raiders
    -0.07
    ACC
    -0.07
    (buffer
    -0.06
    secs
    -0.06
     LD
    -0.06
    STDOUT
    -0.06
    775
    -0.06
    sns
    -0.06
     Worce
    -0.06
    842
    -0.06
    POSITIVE LOGITS
    .partner
    0.07
    ank
    0.06
    Seeder
    0.06
     deja
    0.06
    ephir
    0.06
    _eof
    0.06
    Lewis
    0.06
    !==
    0.06
     만들
    0.06
    ريقة
    0.06
    Act Density 0.012%

    No Known Activations