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

    Neuronpedia

    INDEX
    Explanations

    Memorial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FOX
    -0.07
    件事
    -0.07
     Rarity
    -0.07
     treasures
    -0.07
     goofy
    -0.06
     undone
    -0.06
    �
    -0.06
     redraw
    -0.06
    orf
    -0.06
     traumat
    -0.06
    POSITIVE LOGITS
    consider
    0.08
     [...]↵↵
    0.07
    Either
    0.07
     }}"↵
    0.07
    (Expression
    0.07
    either
    0.07
    ﮎ
    0.07
     considers
    0.07
     interior
    0.07
    的身体
    0.06
    Act Density 0.057%

    No Known Activations