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

    Neuronpedia

    INDEX
    Explanations

    address label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ajuda
    0.59
     υπάρχ
    0.58
    بر
    0.55
     الاجتماعي
    0.55
    د
    0.55
     اقت
    0.54
     helfen
    0.54
    arbeiter
    0.54
     استخدم
    0.53
     impulso
    0.52
    POSITIVE LOGITS
     Address
    0.92
    Address
    0.89
     address
    0.87
    Adress
    0.82
    地址
    0.76
    address
    0.76
     addr
    0.76
    getAddress
    0.72
     ADDRESS
    0.72
     I
    0.71
    Act Density 0.019%

    No Known Activations