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

    Neuronpedia

    INDEX
    Explanations

    existing state, context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ini
    0.38
     Mardi
    0.38
     Tata
    0.37
     newcomer
    0.37
     barefoot
    0.37
     توصیه
    0.36
     tutor
    0.36
     Ping
    0.36
     Kochubei
    0.36
     teleport
    0.36
    POSITIVE LOGITS
    existing
    0.61
    Existing
    0.60
    既存
    0.58
     existing
    0.57
     기존
    0.55
     EXISTING
    0.55
    通常の
    0.50
     контек
    0.47
     Existing
    0.46
     일반
    0.46
    Act Density 0.481%

    No Known Activations