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

    Neuronpedia

    INDEX
    Explanations

    heterosexual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Search
    -0.07
     driveway
    -0.07
    我没有
    -0.07
     Lyn
    -0.07
    layan
    -0.07
     Align
    -0.07
    您
    -0.06
              
↵
    -0.06
     lyon
    -0.06
    忻
    -0.06
    POSITIVE LOGITS
    抗体
    0.07
    嬥
    0.07
     committed
    0.07
     genital
    0.06
    ased
    0.06
     powered
    0.06
     obscured
    0.06
    荡
    0.06
    pio
    0.06
    protocol
    0.06
    Act Density 0.008%

    No Known Activations