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

    Neuronpedia

    INDEX
    Explanations

    backticks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lean
    -0.07
     THEY
    -0.07
    Levels
    -0.07
    τικών
    -0.07
    ведите
    -0.07
     PARK
    -0.07
    ixture
    -0.06
    inder
    -0.06
     Going
    -0.06
     Educ
    -0.06
    POSITIVE LOGITS
     mHandler
    0.07
    emailer
    0.07
    .didReceiveMemoryWarning
    0.07
    operative
    0.06
    ());
↵
↵
    0.06
     Dumbledore
    0.06
    追
    0.06
    �
    0.06
    igrationBuilder
    0.06
    ManagedObjectContext
    0.06
    Act Density 0.018%

    No Known Activations