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

    Neuronpedia

    INDEX
    Explanations

    sexualization and exploitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CSP
    0.35
     sogenannte
    0.35
     fecal
    0.35
     মিলিয়ে
    0.35
     الطريق
    0.34
     The
    0.34
     നൽക
    0.33
     Dienst
    0.33
     Jet
    0.33
    ดวก
    0.33
    POSITIVE LOGITS
     of
    0.75
     của
    0.59
     của
    0.58
     ofthe
    0.57
    of
    0.53
    sof
    0.48
    ຂອງ
    0.48
    ของ
    0.47
     thereof
    0.47
    ِ
    0.44
    Act Density 0.180%

    No Known Activations