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

    Neuronpedia

    INDEX
    Explanations

    seem naturally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ʇ
    0.45
     ironing
    0.44
    ocyclic
    0.41
    HashSet
    0.40
     irons
    0.40
    Morgan
    0.40
     केंद्रों
    0.40
    鹿児島
    0.39
    న్నా
    0.39
    地の
    0.39
    POSITIVE LOGITS
     đoán
    0.46
    CHREIB
    0.40
     πληροφο
    0.39
     వచ్చ
    0.39
    adz
    0.38
    data
    0.38
     typed
    0.38
     Managed
    0.37
    fromParams
    0.37
    arts
    0.36
    Act Density 0.004%

    No Known Activations