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

    Neuronpedia

    INDEX
    Explanations

    agency to sexual attractiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    feder
    0.47
    Feder
    0.39
     tež
    0.38
     cérémon
    0.38
     дори
    0.38
     izol
    0.38
     feder
    0.38
    RECENT
    0.38
    tuple
    0.37
     amore
    0.37
    POSITIVE LOGITS
    식회사
    0.45
    荕
    0.44
     фаразы
    0.43
    ಾಯಕ
    0.42
    oloog
    0.42
     sitio
    0.42
    遐
    0.41
    或其他
    0.41
    শব
    0.41
    佲
    0.40
    Act Density 0.004%

    No Known Activations