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

    Neuronpedia

    INDEX
    Explanations

    classical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autonom
    -0.07
    .confirm
    -0.06
     Trot
    -0.06
     folder
    -0.06
     verb
    -0.06
    意见
    -0.06
     throughput
    -0.06
    SWEP
    -0.06
    _thresh
    -0.06
    blog
    -0.06
    POSITIVE LOGITS
     classical
    0.14
     Classical
    0.12
     burnt
    0.07
    CLASS
    0.07
     thời
    0.07
    ая
    0.07
    `);↵
    0.07
     ma
    0.07
     Rooms
    0.07
     CLASS
    0.06
    Act Density 0.005%

    No Known Activations