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

    Neuronpedia

    INDEX
    Explanations

    not just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    회
    0.47
     velocidades
    0.44
    د
    0.43
     حصے
    0.42
    Произ
    0.41
    敝
    0.41
    Install
    0.40
    溘
    0.40
    Smart
    0.40
     tejto
    0.39
    POSITIVE LOGITS
     tiver
    0.44
    ’
    0.43
     anion
    0.41
     there
    0.41
     peptide
    0.41
     tylko
    0.41
    isi
    0.40
    ’;
    0.40
    idet
    0.39
     Genet
    0.39
    Act Density 0.005%

    No Known Activations