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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fortune
    -0.07
     Bengals
    -0.07
     piss
    -0.07
     fc
    -0.07
    籽
    -0.07
     Waist
    -0.07
     tentative
    -0.06
     Unexpected
    -0.06
    .games
    -0.06
    ici
    -0.06
    POSITIVE LOGITS
    deb
    0.07
     Buenos
    0.07
    别人的
    0.07
    0.07
     Ingram
    0.07
    >>;↵
    0.07
    ⇵
    0.07
     중요한
    0.07
     désorm
    0.07
     zwar
    0.07
    Act Density 0.006%

    No Known Activations