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

    Neuronpedia

    INDEX
    Explanations

    CP violation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Framework
    -0.06
    елей
    -0.06
     sequencing
    -0.06
    .deep
    -0.06
    Sequential
    -0.06
    isEmpty
    -0.06
     دي
    -0.06
     Теп
    -0.06
    obic
    -0.06
    toupper
    -0.06
    POSITIVE LOGITS
     salario
    0.08
    ...");↵↵
    0.07
     wallets
    0.07
     """↵↵
    0.07
     });
↵
↵
    0.06
     fails
    0.06
     });↵↵
    0.06
    "
↵
↵
    0.06
     """
↵
↵
    0.06
     novelist
    0.06
    Act Density 0.007%

    No Known Activations