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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _append
    -0.07
    Dismiss
    -0.06
     millet
    -0.06
     Estr
    -0.06
    年的
    -0.06
    client
    -0.06
    onClick
    -0.06
    ETwitter
    -0.06
    _FINISH
    -0.06
    申
    -0.06
    POSITIVE LOGITS
     bureaucr
    0.07
    ดร
    0.07
    .VERSION
    0.07
     CW
    0.07
    aka
    0.07
    ीछ
    0.06
    uluğu
    0.06
     Barrett
    0.06
     bg
    0.06
    br
    0.06
    Act Density 0.005%

    No Known Activations