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

    Neuronpedia

    INDEX
    Explanations

    best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mins
    0.89
    mins
    0.79
    minute
    0.77
     prototypical
    0.76
    בר
    0.71
     hrs
    0.71
     minutes
    0.68
    Defining
    0.68
     Plays
    0.68
    deque
    0.68
    POSITIVE LOGITS
     BEST
    1.13
     best
    1.10
    BEST
    1.04
     луч
    0.94
     meilleure
    0.94
     najleps
    0.87
     terbaik
    0.86
     лучший
    0.86
    best
    0.85
     Best
    0.85
    Act Density 0.000%

    No Known Activations