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

    Neuronpedia

    INDEX
    Explanations

    State

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     หล
    -0.07
     Ну
    -0.07
    川
    -0.06
    之间
    -0.06
    bits
    -0.06
     loans
    -0.06
     알고
    -0.06
     bursting
    -0.06
     Schw
    -0.06
    Wind
    -0.06
    POSITIVE LOGITS
     ISIS
    0.07
     slick
    0.07
     Citadel
    0.07
    heartbeat
    0.06
    .assertNot
    0.06
    OfMonth
    0.06
    -ste
    0.06
    -D
    0.06
     isLoading
    0.06
    MD
    0.06
    Act Density 0.003%

    No Known Activations