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

    Neuronpedia

    INDEX
    Explanations

    sequence modeling, generation, labeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    岗位
    0.44
    試合
    0.40
    isin
    0.39
    amsu
    0.38
     capricious
    0.38
    aided
    0.37
    ▾
    0.37
    وران
    0.37
    ete
    0.36
     sprawd
    0.36
    POSITIVE LOGITS
    Seq
    0.82
    Sequ
    0.82
     sequ
    0.77
     seq
    0.77
     Sequ
    0.77
     Seq
    0.76
     Sequences
    0.75
     SEQU
    0.74
     sequences
    0.73
     Sequence
    0.70
    Act Density 0.012%

    No Known Activations