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

    Neuronpedia

    INDEX
    Explanations

    mind: confusion of mind: chill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    steak
    0.89
    speople
    0.89
    surgeon
    0.88
    s
    0.88
    core
    0.84
    sheet
    0.80
    BUF
    0.79
    runner
    0.79
    PCS
    0.78
    LFT
    0.77
    POSITIVE LOGITS
     लेकर
    0.80
     descon
    0.69
     е
    0.68
    िल्‍
    0.68
     после
    0.68
     dominated
    0.68
     το
    0.66
     располага
    0.65
     indag
    0.65
     скри
    0.65
    Act Density 0.002%

    No Known Activations