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

    Neuronpedia

    INDEX
    Explanations

    recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _confirm
    -0.07
    іл
    -0.07
     notification
    -0.07
    اگ
    -0.07
     oxide
    -0.06
     nghệ
    -0.06
     segregated
    -0.06
     cows
    -0.06
    web
    -0.06
     Belmont
    -0.06
    POSITIVE LOGITS
    (da
    0.06
     ldc
    0.06
    (Core
    0.06
    /basic
    0.06
    requires
    0.06
    Sending
    0.06
     quieter
    0.06
    Assistant
    0.06
     dout
    0.06
    .flags
    0.06
    Act Density 0.008%

    No Known Activations