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

    Neuronpedia

    INDEX
    Explanations

    APIs and interfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ou
    -0.08
     Lite
    -0.07
     encompasses
    -0.07
    OU
    -0.07
     dust
    -0.07
    tty
    -0.06
     configuring
    -0.06
     mappings
    -0.06
    olving
    -0.06
     Specify
    -0.06
    POSITIVE LOGITS
     eject
    0.07
     zveřej
    0.07
     defaultdict
    0.07
    .bot
    0.06
    -Javadoc
    0.06
    .relu
    0.06
     Venue
    0.06
     توم
    0.06
    createQueryBuilder
    0.06
    .setCancelable
    0.06
    Act Density 0.328%

    No Known Activations