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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     варт
    -0.06
    Screenshot
    -0.06
     doanh
    -0.06
     Institutional
    -0.06
    _FINISH
    -0.06
    _skip
    -0.06
    �
    -0.06
    .…↵↵
    -0.06
     kali
    -0.06
     compl
    -0.06
    POSITIVE LOGITS
     few
    0.07
    ونه
    0.07
     caffe
    0.06
    Morning
    0.06
    jie
    0.06
     OFFSET
    0.06
     abortion
    0.06
     DATABASE
    0.06
    χος
    0.06
     adicion
    0.06
    Act Density 0.020%

    No Known Activations