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

    Neuronpedia

    INDEX
    Explanations

    sexual preferences or relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.34
     d
    0.30
    OF
    0.29
     RAM
    0.29
     W
    0.29
    or
    0.28
     &
    0.28
     memory
    0.28
    s
    0.27
    ↵↵
    0.27
    POSITIVE LOGITS
    噘
    0.32
     earnestly
    0.31
     shitty
    0.31
    కునే
    0.31
    有所
    0.30
     lesbian
    0.29
     numberWith
    0.29
     nameWithOwner
    0.29
     lesbians
    0.29
     поговори
    0.29
    Act Density 0.001%

    No Known Activations