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

    Neuronpedia

    INDEX
    Explanations

    Android UI code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     작
    -0.07
     две
    -0.07
    -generation
    -0.07
    dp
    -0.06
    眼睛
    -0.06
    Knight
    -0.06
    verb
    -0.06
    npc
    -0.06
    846
    -0.06
    431
    -0.06
    POSITIVE LOGITS
     ancora
    0.07
    便
    0.07
     Len
    0.07
     Status
    0.06
     تقس
    0.06
     pct
    0.06
    igits
    0.06
    ":"",↵
    0.06
    ERICA
    0.06
    帮助
    0.06
    Act Density 0.021%

    No Known Activations