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

    Neuronpedia

    INDEX
    Explanations

    insurance, therapy, leak, spray, rest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     നിരവധി
    0.49
    たくさんの
    0.48
    いろんな
    0.48
     jedes
    0.48
    最適な
    0.48
     życiu
    0.47
     eventuali
    0.46
     countless
    0.46
    ূর্ব
    0.46
    icolored
    0.44
    POSITIVE LOGITS
    T
    0.56
     and
    0.50
     for
    0.48
     For
    0.48
     of
    0.46
    R
    0.46
     system
    0.45
     T
    0.45
    L
    0.45
    in
    0.43
    Act Density 0.034%

    No Known Activations