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

    Neuronpedia

    INDEX
    Explanations

    in the middle of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     than
    0.47
    ¹
    0.46
     on
    0.43
    šek
    0.41
     Than
    0.41
     towards
    0.40
     একজনের
    0.40
    ¹)
    0.40
     enteros
    0.40
     Venue
    0.39
    POSITIVE LOGITS
     midst
    0.93
     amidst
    0.83
    Amid
    0.77
     surrounded
    0.68
     Amid
    0.67
     rubble
    0.61
     amid
    0.61
     가운데
    0.61
     Surrounded
    0.61
     መካከል
    0.61
    Act Density 0.028%

    No Known Activations