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

    Neuronpedia

    INDEX
    Explanations

    procedure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .storage
    -0.08
     Shore
    -0.08
    存货
    -0.07
     порядке
    -0.07
    赚
    -0.07
    (sock
    -0.07
    (Frame
    -0.06
    END
    -0.06
    .sender
    -0.06
     floors
    -0.06
    POSITIVE LOGITS
    䗖
    0.08
     disgusting
    0.08
    优美
    0.07
     Gala
    0.07
    เกา
    0.07
     topics
    0.07
     roman
    0.07
     alignItems
    0.07
    Japanese
    0.07
    🤮
    0.07
    Act Density 0.007%

    No Known Activations