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

    Neuronpedia

    INDEX
    Explanations

    Ad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    insula
    -0.07
     //////////
    -0.07
     HttpMethod
    -0.07
    /configuration
    -0.07
    どの
    -0.07
    铤
    -0.07
    ょう
    -0.07
     Tor
    -0.07
     Tháng
    -0.07
     destined
    -0.07
    POSITIVE LOGITS
    富含
    0.06
     sighed
    0.06
    fill
    0.06
    回调
    0.06
    EGA
    0.06
    课文
    0.06
     wrote
    0.06
     GD
    0.06
    _ADDRESS
    0.06
    投稿
    0.06
    Act Density 0.002%

    No Known Activations