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

    Neuronpedia

    INDEX
    Explanations

    deadline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ου
    1.75
     has
    1.71
    दिल्ली
    1.70
    1.69
    ['
    1.63
    िक
    1.60
     is
    1.59
    ystem
    1.59
    thing
    1.57
    ر
    1.57
    POSITIVE LOGITS
    Е
    1.34
    Ң
    1.30
    lech
    1.23
     ڪر
    1.22
    ל
    1.22
     deadlines
    1.21
    סטי
    1.19
    DARK
    1.19
     चाहि
    1.18
     Php
    1.14
    Act Density 0.041%

    No Known Activations