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

    Neuronpedia

    INDEX
    Explanations

    sexual act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     видел
    0.48
     защиты
    0.46
     gland
    0.46
     gobl
    0.45
     glandular
    0.45
     whanne
    0.43
     prost
    0.43
     assistants
    0.43
     фигу
    0.43
     depois
    0.43
    POSITIVE LOGITS
    n
    0.59
    il
    0.57
    sekten
    0.50
    ir
    0.49
    ar
    0.46
    Revised
    0.45
    ລິ
    0.44
    Engagement
    0.44
    ke
    0.42
    ac
    0.42
    Act Density 0.000%

    No Known Activations