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

    Neuronpedia

    INDEX
    Explanations

    women's underwear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ACES
    0.73
     tunnels
    0.72
    ăș
    0.70
     tunnelling
    0.67
     tunneling
    0.64
    rollen
    0.63
    aces
    0.63
    AGES
    0.63
     AUTHORS
    0.63
     complic
    0.61
    POSITIVE LOGITS
     Sasha
    0.94
    匏
    0.89
    derm
    0.86
    emiah
    0.84
     jefe
    0.84
     harem
    0.84
    t
    0.84
    dě
    0.83
     desember
    0.82
     alrededor
    0.82
    Act Density 0.000%

    No Known Activations