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

    Neuronpedia

    INDEX
    Explanations

    rap, Yo, tea, girl, b

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     편리
    1.02
    ılan
    0.95
     sağlar
    0.87
     säker
    0.81
     효율
    0.81
     homely
    0.80
     käyttö
    0.80
     objections
    0.80
     toiletries
    0.79
     används
    0.79
    POSITIVE LOGITS
    1
    0.97
    Rap
    0.91
    Platinum
    0.89
    3
    0.86
    PN
    0.86
    centric
    0.84
    platinum
    0.84
    Luxury
    0.84
    Hip
    0.83
    $
    0.83
    Act Density 0.119%

    No Known Activations