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

    Neuronpedia

    INDEX
    Explanations

    install

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atches
    -0.07
    caffe
    -0.07
     Heck
    -0.07
     coarse
    -0.07
    哈利
    -0.07
    清净
    -0.07
    ᨧ
    -0.07
     שר
    -0.07
    إبد
    -0.06
     '*.
    -0.06
    POSITIVE LOGITS
     Various
    0.07
    (URL
    0.07
    ניוזל
    0.07
    /J
    0.07
    VM
    0.07
     Mk
    0.06
     вообще
    0.06
    网购
    0.06
     GUI
    0.06
     Multiple
    0.06
    Act Density 0.001%

    No Known Activations