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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chap
    -0.07
    잽
    -0.07
     Bart
    -0.07
    找出
    -0.07
     trẻ
    -0.07
    Were
    -0.07
     ghế
    -0.07
    anco
    -0.06
    ƨ
    -0.06
    sp
    -0.06
    POSITIVE LOGITS
     особенно
    0.08
    錾
    0.07
    了我的
    0.07
    icians
    0.07
     decentral
    0.07
     specialists
    0.07
    一定的
    0.07
    แตก
    0.07
     Formats
    0.07
     loyalty
    0.07
    Act Density 0.002%

    No Known Activations