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

    Neuronpedia

    INDEX
    Explanations

    common phrases and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    id
    0.65
    S
    0.54
    etc
    0.50
    url
    0.48
    N
    0.48
     None
    0.48
    if
    0.48
    T
    0.47
    C
    0.47
    >>
    0.46
    POSITIVE LOGITS
     reali
    0.49
     Bakufu
    0.47
     antena
    0.46
     appre
    0.45
     puppet
    0.45
     tô
    0.44
    勐
    0.44
     moulded
    0.43
     է
    0.43
    ຸດ
    0.43
    Act Density 0.001%

    No Known Activations