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

    Neuronpedia

    INDEX
    Explanations

    **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    builtin
    0.70
    matmul
    0.63
    ilizce
    0.63
    iple
    0.62
     fruition
    0.62
     however
    0.62
    ortium
    0.61
    verbose
    0.61
    eyJ
    0.60
    encoder
    0.60
    POSITIVE LOGITS
     -
    0.96
    <
    0.95
     (*
    0.94
     –
    0.90
     başlı
    0.88
    så
    0.87
    (**
    0.87
    nın
    0.86
    _[
    0.85
    :[
    0.85
    Act Density 0.733%

    No Known Activations