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

    Neuronpedia

    INDEX
    Explanations

    Code/programming counters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    broadcast
    -0.08
    加盟
    -0.08
    Matched
    -0.07
     phù
    -0.07
     Leistungen
    -0.07
    estock
    -0.07
     estates
    -0.07
     pregnant
    -0.07
    vec
    -0.07
    arr
    -0.07
    POSITIVE LOGITS
     amusing
    0.11
     togg
    0.11
     contador
    0.11
     버튼
    0.11
     Clicking
    0.10
     silly
    0.10
     点击
    0.10
     toggle
    0.10
     clicked
    0.10
     Toggle
    0.10
    Act Density 0.010%

    No Known Activations