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

    Neuronpedia

    INDEX
    Explanations

    unusual symbols or emojis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dok
    -0.06
    Career
    -0.06
    Bright
    -0.06
     Presidency
    -0.06
    ан
    -0.06
    -क
    -0.06
    Fac
    -0.06
    Fa
    -0.06
    Bell
    -0.06
    Keith
    -0.06
    POSITIVE LOGITS
    или
    0.07
     вида
    0.07
    .ALIGN
    0.06
    ViewModel
    0.06
    (eventName
    0.06
     Shuttle
    0.06
     которой
    0.06
     이름
    0.06
    BMW
    0.06
     Democracy
    0.06
    Act Density 0.007%

    No Known Activations