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

    Neuronpedia

    INDEX
    Explanations

    LIABLE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prá
    -0.07
    ụ
    -0.07
     若
    -0.07
     cre
    -0.06
     zayıf
    -0.06
    _CUR
    -0.06
     transient
    -0.06
    istrat
    -0.06
     wlan
    -0.06
     frü
    -0.06
    POSITIVE LOGITS
    こちら
    0.08
    경
    0.08
    TL
    0.07
     경
    0.07
    .stdin
    0.07
     Mohammed
    0.06
     Hawai
    0.06
    approx
    0.06
     Speedway
    0.06
    feeding
    0.06
    Act Density 0.001%

    No Known Activations