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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    ovic
    -0.07
    iyat
    -0.06
    reh
    -0.06
     Ot
    -0.06
    Thomas
    -0.06
     Cục
    -0.06
     Tổng
    -0.06
    ูป
    -0.06
    틱
    -0.06
    POSITIVE LOGITS
     hur
    0.07
     equivalence
    0.07
     battling
    0.07
    (script
    0.07
     viv
    0.06
     LAN
    0.06
     Motors
    0.06
    /csv
    0.06
     basket
    0.06
     elev
    0.06
    Act Density 0.001%

    No Known Activations