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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    luví
    -0.07
    _hw
    -0.07
    /comments
    -0.07
    агато
    -0.06
     HW
    -0.06
     brut
    -0.06
    imeters
    -0.06
     ダ
    -0.06
    ومتر
    -0.06
    _HERE
    -0.06
    POSITIVE LOGITS
     TI
    0.07
    (sockfd
    0.07
    所
    0.07
    视频
    0.06
     خویش
    0.06
    (plot
    0.06
     фун
    0.06
    iag
    0.06
     ngôi
    0.06
    (col
    0.06
    Act Density 0.059%

    No Known Activations