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

    Neuronpedia

    INDEX
    Explanations

    out of office

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Slovakia
    0.62
     AMOLED
    0.60
     ofrecemos
    0.60
     Walther
    0.59
     Industri
    0.58
     Gaming
    0.57
     Größen
    0.57
     DKI
    0.55
     Pab
    0.54
     เล่น
    0.54
    POSITIVE LOGITS
     শ্ব
    0.64
    Consistency
    0.62
    Personally
    0.61
    plugin
    0.59
    续
    0.59
     shoving
    0.57
    家的
    0.57
     continual
    0.56
     plugin
    0.55
    الق
    0.55
    Act Density 0.000%

    No Known Activations