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

    Neuronpedia

    INDEX
    Explanations

    dramatic play

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     względu
    0.91
     datt
    0.89
     pelvis
    0.88
     plast
    0.88
     perone
    0.85
     kary
    0.84
     sikk
    0.84
     barr
    0.83
    čka
    0.83
     sû
    0.83
    POSITIVE LOGITS
    ديد
    1.08
     দেখিয়া
    0.84
    ০০
    0.79
    <0x80>
    0.77
    État
    0.77
    Log
    0.76
    MBOLS
    0.75
     особое
    0.75
    ای
    0.75
     эксперимента
    0.75
    Act Density 0.000%

    No Known Activations