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

    Neuronpedia

    INDEX
    Explanations

    wolf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debut
    -0.08
    ondon
    -0.07
    >d
    -0.07
    sahuje
    -0.07
     věci
    -0.06
     beginner
    -0.06
     AUTH
    -0.06
     mains
    -0.06
    Address
    -0.06
     Webster
    -0.06
    POSITIVE LOGITS
    狼
    0.07
    овер
    0.07
     kiểm
    0.07
    kowski
    0.07
    ł
    0.07
     implying
    0.07
     Wolfe
    0.06
     testify
    0.06
     Wolf
    0.06
     kö
    0.06
    Act Density 0.013%

    No Known Activations