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

    Neuronpedia

    INDEX
    Explanations

    Citations in research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Parsing
    -0.07
     bum
    -0.07
    (**
    -0.06
     αρχ
    -0.06
     Canadiens
    -0.06
    �
    -0.06
    .addValue
    -0.06
     Donna
    -0.06
    �
    -0.06
     Row
    -0.06
    POSITIVE LOGITS
    ization
    0.07
    setQuery
    0.07
    NSObject
    0.07
    maj
    0.06
    ';↵↵↵↵
    0.06
    енти
    0.06
    */
↵
↵
    0.06
    олод
    0.06
    running
    0.06
    //=
    0.06
    Act Density 0.006%

    No Known Activations