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

    Neuronpedia

    INDEX
    Explanations

    EU funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    合せ
    0.48
     temper
    0.40
     presion
    0.39
    पे
    0.38
     tempting
    0.38
     bruise
    0.38
     consulté
    0.38
    अर्स
    0.38
    кы
    0.38
    ทะ
    0.37
    POSITIVE LOGITS
     ప్రా
    0.36
    ayd
    0.36
     utilization
    0.35
    یوں
    0.35
     tunnelling
    0.35
     filings
    0.35
    ricing
    0.35
     utilized
    0.35
     compiles
    0.35
    ulation
    0.34
    Act Density 0.010%

    No Known Activations