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

    Neuronpedia

    INDEX
    Explanations

    sexual content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MATERIAL
    -0.07
    ROSS
    -0.07
    	set
    -0.06
    [result
    -0.06
     latent
    -0.06
    GD
    -0.06
    phet
    -0.06
     Decorating
    -0.06
     eens
    -0.06
    ross
    -0.06
    POSITIVE LOGITS
    -region
    0.08
    .onNext
    0.07
    景
    0.07
     Schumer
    0.06
    верж
    0.06
    \Collections
    0.06
     Pornhub
    0.06
    ！”↵↵
    0.06
     sdk
    0.06
    ))))↵↵
    0.06
    Act Density 0.002%

    No Known Activations