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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    covering
    -0.07
     Fathers
    -0.07
    Guide
    -0.06
    Offset
    -0.06
    uses
    -0.06
     Suit
    -0.06
    apos
    -0.06
    ongo
    -0.06
    dist
    -0.06
     caracteres
    -0.06
    POSITIVE LOGITS
     میکن
    0.07
     infrastructure
    0.07
    prices
    0.06
    отв
    0.06
    bows
    0.06
    CADE
    0.06
    /DD
    0.06
    .SpringApplication
    0.06
     Becky
    0.06
     Seit
    0.06
    Act Density 0.028%

    No Known Activations