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

    Neuronpedia

    INDEX
    Explanations

    proof of reserves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     This
    0.58
     Lay
    0.48
     It
    0.47
     Scheme
    0.45
     *
    0.45
     Add
    0.44
     и
    0.44
     Disclosure
    0.44
     Correct
    0.43
     و
    0.42
    POSITIVE LOGITS
    ینڈ
    0.48
     campuran
    0.47
     spok
    0.46
    protos
    0.45
     innego
    0.45
     drugi
    0.45
     karoti
    0.44
    ্টর
    0.44
     protos
    0.43
    tempHeader
    0.43
    Act Density 0.000%

    No Known Activations