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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "zu" and its variations, which indicate direction or addition in German

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    zu formzu beendenzu Versuchzu Verfügungzu Förderung

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sánchez
    -0.48
     ainfi
    -0.48
     Turquía
    -0.48
     Polsek
    -0.48
     Irán
    -0.47
    Encyklopedia
    -0.47
    CppMethod
    -0.47
     Tatsache
    -0.46
     enfans
    -0.46
     península
    -0.45
    POSITIVE LOGITS
     zu
    1.74
     Zu
    1.32
    Zu
    1.30
     ZU
    1.19
    zu
    0.96
    ZU
    0.84
     To
    0.71
    To
    0.70
     aufzu
    0.69
     TO
    0.69
    Act Density 0.000%

    No Known Activations