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

    Neuronpedia

    INDEX
    Explanations

    ovaries and females produce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gu
    0.45
    ravés
    0.43
    ueva
    0.42
    eni
    0.40
     выяв
    0.39
    a
    0.38
    research
    0.38
     සා
    0.38
    uego
    0.37
     través
    0.37
    POSITIVE LOGITS
     TELE
    0.43
    煖
    0.42
    曈
    0.41
     squre
    0.41
     👀
    0.41
    👀
    0.41
    isateur
    0.41
    اشة
    0.40
     télé
    0.40
     Télé
    0.39
    Act Density 0.003%

    No Known Activations