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

    Neuronpedia

    INDEX
    Explanations

    a lot of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     svojim
    0.45
     svojih
    0.45
    daki
    0.44
     собственной
    0.43
     eigenes
    0.43
    Synced
    0.42
    ordat
    0.40
    是最
    0.40
    自身的
    0.40
     자신의
    0.39
    POSITIVE LOGITS
     reason
    0.64
     involved
    0.59
     plenty
    0.52
     disponibles
    0.52
     available
    0.52
     inherent
    0.52
     difference
    0.51
     here
    0.50
     doubt
    0.49
     disponible
    0.46
    Act Density 0.020%

    No Known Activations