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

    Neuronpedia

    INDEX
    Explanations

    say "r" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CL
    -0.07
    alloween
    -0.07
    libraries
    -0.06
     Lori
    -0.06
    <DateTime
    -0.06
    iene
    -0.06
    .weixin
    -0.06
    udging
    -0.06
    (depend
    -0.06
    ash
    -0.06
    POSITIVE LOGITS
     Photos
    0.07
     vag
    0.06
    match
    0.06
     Siri
    0.06
    射
    0.06
     sacked
    0.06
     віз
    0.06
    tag
    0.06
     SZ
    0.06
     trà
    0.06
    Act Density 0.006%

    No Known Activations