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

    Neuronpedia

    INDEX
    Explanations

    formatting decimal places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h2>
    0.63
    ill
    0.63
    ช
    0.61
     Some
    0.59
     Swans
    0.58
    zyc
    0.56
     Sail
    0.56
     Helicopter
    0.56
     this
    0.54
     Several
    0.54
    POSITIVE LOGITS
    en
    0.89
    formatted
    0.68
    asctime
    0.61
     সময়ে
    0.61
     formatted
    0.61
    ený
    0.60
    ANCIAL
    0.60
    )|$(
    0.59
     (\%)
    0.58
     माध्य
    0.55
    Act Density 0.082%

    No Known Activations