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

    Neuronpedia

    INDEX
    Explanations

    list separators and terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nota
    1.25
    aj
    1.20
     νέα
    1.18
     tierra
    1.18
     τα
    1.16
     mimo
    1.15
    ுகிறது
    1.14
     encarg
    1.14
    buf
    1.12
    鬟
    1.11
    POSITIVE LOGITS
     silam
    1.22
    ت
    1.22
    Есть
    1.19
    Игра
    1.18
    سال
    1.18
    Здравствуйте
    1.16
    Votre
    1.15
    Professional
    1.15
    Attrs
    1.15
    have
    1.15
    Act Density 0.000%

    No Known Activations