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

    Neuronpedia

    INDEX
    Explanations

    scams, destruction, specifies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EMEA
    0.50
     RAID
    0.50
     AWD
    0.47
     Capricorn
    0.47
     UAE
    0.46
    SelectSingleNode
    0.45
     Agents
    0.45
     Persian
    0.42
     stain
    0.42
     turbulent
    0.42
    POSITIVE LOGITS
    repetitions
    0.48
    螂
    0.47
    扌
    0.46
    licks
    0.46
     ولی
    0.45
    SalesRep
    0.45
    烀
    0.45
     -!
    0.44
     ولي
    0.43
    iter
    0.43
    Act Density 0.001%

    No Known Activations