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

    Neuronpedia

    INDEX
    Explanations

    freedom from interference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     całej
    0.37
    ണ്യ
    0.36
     peroxide
    0.35
    规划
    0.35
    crate
    0.34
    从未
    0.34
    мами
    0.33
     conservatively
    0.33
    acceler
    0.33
    àm
    0.33
    POSITIVE LOGITS
     싱
    0.43
    Nc
    0.41
    ុល
    0.40
    nels
    0.40
     cfp
    0.40
    恿
    0.40
     Raffle
    0.39
     اعت
    0.39
     sive
    0.38
     timeCounter
    0.38
    Act Density 0.000%

    No Known Activations