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

    Neuronpedia

    INDEX
    Explanations

    Math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uns
    -0.07
    Comb
    -0.07
    ង្គ
    -0.07
    .Initialize
    -0.07
    .initialize
    -0.07
     speculation
    -0.07
     �
    -0.07
    geschichte
    -0.07
    ರಿಗೆ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     */
↵
↵
    0.09
     discre
    0.08
     */↵↵↵
    0.08
    スター
    0.08
     оқ
    0.08
     ){
↵
    0.08
     yos
    0.08
     */↵↵↵/
    0.08
     beauties
    0.08
    Namun
    0.07
    Act Density 0.007%

    No Known Activations