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

    Neuronpedia

    INDEX
    Explanations

    has/have then verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trailbl
    0.84
     spectacularly
    0.83
     Letting
    0.82
     staked
    0.82
     tinkering
    0.81
     whips
    0.81
     Blogging
    0.79
     sprinkled
    0.79
    𝚔
    0.79
     graced
    0.78
    POSITIVE LOGITS
    Three
    0.93
    three
    0.92
    Different
    0.92
    two
    0.91
     three
    0.89
    Few
    0.89
    Two
    0.87
    一行
    0.83
     trois
    0.83
    Own
    0.83
    Act Density 0.037%

    No Known Activations