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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mine
    1.13
     Mine
    1.11
    mine
    0.87
     mines
    0.86
     mine
    0.84
    MINE
    0.76
    mines
    0.70
    자의
    0.65
     Mines
    0.65
    Mining
    0.62
    POSITIVE LOGITS
     him
    2.84
     them
    2.73
     me
    2.37
    them
    2.30
     us
    2.22
    him
    2.06
     Them
    2.02
     THEM
    2.00
     них
    1.96
     Him
    1.96
    Act Density 0.268%

    No Known Activations