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

    Neuronpedia

    INDEX
    Explanations

    know your customer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iseries
    0.78
    গুল
    0.68
     ubiquitin
    0.63
    ຕ
    0.62
    Travis
    0.62
     tens
    0.62
     interpolated
    0.62
    নির্ম
    0.61
     terv
    0.61
    phalt
    0.61
    POSITIVE LOGITS
    ledge
    1.85
    lege
    1.79
    ledged
    1.76
    led
    1.48
     ledge
    1.44
    ledger
    1.38
    lede
    1.37
    ldg
    1.28
    leg
    1.24
    ingly
    1.23
    Act Density 0.021%

    No Known Activations