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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dân
    -0.07
     Numbers
    -0.07
     land
    -0.06
     BRA
    -0.06
     Citizens
    -0.06
     Expenses
    -0.06
    /users
    -0.06
     Lords
    -0.06
     Decoder
    -0.06
    .Direct
    -0.06
    POSITIVE LOGITS
     <-
    0.07
    viewController
    0.07
    腿
    0.07
    чає
    0.07
     Clara
    0.07
    mente
    0.07
    ringe
    0.06
    ogenesis
    0.06
     örg
    0.06
    aramel
    0.06
    Act Density 0.016%

    No Known Activations