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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feliz
    -0.07
    霸王
    -0.07
    IPP
    -0.07
     listening
    -0.07
     signaling
    -0.07
     Suppliers
    -0.07
     Sight
    -0.07
     getInstance
    -0.07
    卺
    -0.06
    抵制
    -0.06
    POSITIVE LOGITS
    评定
    0.07
    全镇
    0.07
    =input
    0.07
     "+
    0.07
     angered
    0.06
    "+
    0.06
    官方
    0.06
     tuyên
    0.06
    _audio
    0.06
    .Player
    0.06
    Act Density 0.039%

    No Known Activations