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

    Neuronpedia

    INDEX
    Explanations

    well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .swap
    -0.07
     shred
    -0.07
     nada
    -0.07
    镭
    -0.07
    й
    -0.07
    行為
    -0.07
    ڽ
    -0.07
     Scot
    -0.07
    抗氧化
    -0.07
    渗
    -0.06
    POSITIVE LOGITS
     enrolled
    0.08
    Ton
    0.07
    ﭱ
    0.07
    حضار
    0.07
    /front
    0.07
    �
    0.06
    clicked
    0.06
    ител
    0.06
    酸
    0.06
     Freel
    0.06
    Act Density 0.012%

    No Known Activations