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

    Neuronpedia

    INDEX
    Explanations

    Tweet handles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     )->
    -0.08
     */
↵
    -0.08
     />
↵
    -0.08
    ."]↵
    -0.07
     shouldn't
    -0.07
    wein
    -0.07
     *)↵↵
    -0.07
    ;">
↵
    -0.07
    );↵/
    -0.07
    仅
    -0.07
    POSITIVE LOGITS
    UBA
    0.08
     revolutionary
    0.08
     дому
    0.07
    ωνα
    0.07
     riferimento
    0.07
     председ
    0.07
     составе
    0.07
    (reference
    0.07
     premi
    0.07
    Hu
    0.07
    Act Density 0.441%

    No Known Activations