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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⇙
    -0.08
    暂停
    -0.08
    وني
    -0.08
    /rs
    -0.08
    个城市
    -0.07
    tempt
    -0.07
    획
    -0.07
    头脑
    -0.07
     Turkey
    -0.07
     Hop
    -0.06
    POSITIVE LOGITS
    velte
    0.08
     diret
    0.07
    .Concat
    0.07
     Merrill
    0.07
    BIND
    0.06
    (RE
    0.06
     Rev
    0.06
     hợ
    0.06
    _AUD
    0.06
     bitrate
    0.06
    Act Density 0.013%

    No Known Activations