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

    Neuronpedia

    INDEX
    Explanations

    counter and next assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     выгля
    0.50
     worded
    0.44
     beast
    0.43
     именем
    0.41
     huge
    0.40
     names
    0.39
     adorned
    0.38
    კი
    0.38
     asserts
    0.38
     имя
    0.38
    POSITIVE LOGITS
     سایر
    0.49
     ہونے
    0.46
     andra
    0.45
    ateurs
    0.43
     কার্যক্রম
    0.42
     Howe
    0.42
    ાય
    0.41
     Ressources
    0.41
     estacion
    0.40
    的其他
    0.40
    Act Density 0.004%

    No Known Activations