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

    Neuronpedia

    INDEX
    Explanations

    collect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corridor
    -0.09
     hari
    -0.08
     HSV
    -0.08
     sid
    -0.07
     Axis
    -0.07
     bedside
    -0.07
    霸王
    -0.07
     await
    -0.07
    świad
    -0.07
     cuda
    -0.07
    POSITIVE LOGITS
    삷
    0.07
    fection
    0.07
     Republicans
    0.07
    чрежден
    0.07
     nonprofits
    0.07
    +$
    0.07
    ,
    0.07
    企业发展
    0.06
    соб
    0.06
    뽄
    0.06
    Act Density 0.038%

    No Known Activations