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

    Neuronpedia

    INDEX
    Explanations

    sets of measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.95
    深受
    0.80
     অথবা
    0.79
     join
    0.79
     joins
    0.76
     થાય
    0.75
     partners
    0.75
    或其他
    0.73
     allies
    0.73
     partner
    0.73
    POSITIVE LOGITS
    且
    1.00
    Metering
    0.83
    ASCII
    0.83
    Statistic
    0.82
    Statistical
    0.82
    Stainless
    0.81
    Geometric
    0.81
    Expiration
    0.81
    <unused2204>
    0.81
    Limited
    0.80
    Act Density 0.168%

    No Known Activations