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

    Neuronpedia

    INDEX
    Explanations

    al/ul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Readers
    -0.06
     Cover
    -0.06
    ipherals
    -0.06
    quiv
    -0.06
    Steel
    -0.06
    $"
    -0.06
    .Join
    -0.06
     triangles
    -0.06
    anke
    -0.06
    (DBG
    -0.06
    POSITIVE LOGITS
     affect
    0.07
     viewWillAppear
    0.07
     정말
    0.07
    ,re
    0.06
     επι
    0.06
    REL
    0.06
     happiest
    0.06
     art
    0.06
     şeklinde
    0.06
     معل
    0.06
    Act Density 0.005%

    No Known Activations