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

    Neuronpedia

    INDEX
    Explanations

    accessibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    969
    -0.07
    isters
    -0.07
     رس
    -0.07
    キュ
    -0.06
     viewBox
    -0.06
     Sür
    -0.06
     slate
    -0.06
     cabinets
    -0.06
     Eclipse
    -0.06
    -west
    -0.06
    POSITIVE LOGITS
    .IsActive
    0.07
    597
    0.07
    damage
    0.07
    [column
    0.06
    [`
    0.06
     );
↵
    0.06
    TokenType
    0.06
    /plain
    0.06
     -↵
    0.06
    готов
    0.06
    Act Density 0.008%

    No Known Activations