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

    Neuronpedia

    INDEX
    Explanations

    quantifying time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rxd
    0.44
    દે
    0.36
     possibly
    0.35
    findOrFail
    0.35
     المشار
    0.35
    inations
    0.34
     overfitting
    0.34
     Él
    0.34
     continually
    0.34
    Includes
    0.34
    POSITIVE LOGITS
     years
    0.91
     months
    0.72
     Years
    0.67
     weeks
    0.67
    years
    0.64
     hundred
    0.64
     days
    0.63
    Years
    0.62
     años
    0.62
     Jahre
    0.61
    Act Density 0.005%

    No Known Activations