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

    Neuronpedia

    INDEX
    Explanations

    describing states and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лист
    0.40
     Logging
    0.39
    ajar
    0.38
     Warrant
    0.38
    مكن
    0.37
     Gift
    0.37
    ليب
    0.37
     Logs
    0.37
     bibli
    0.36
    Becoming
    0.36
    POSITIVE LOGITS
    ራም
    0.43
     চ্যালেঞ্জ
    0.39
     mü
    0.38
     Συ
    0.38
    hd
    0.37
    🍔
    0.37
    arın
    0.37
    órmula
    0.36
    RELATES
    0.36
     গঙ্গ
    0.36
    Act Density 0.000%

    No Known Activations